Loading video...

Video Failed to Load

Go Home

i created a Claude Skill that makes perfect Framer components & overrides ideal for: - webgl & shaders - CMS-fed items - perfect property controls - react hydration/SSR context - shared states - canvas/preview detection - safari fixes - & so much more github link below ↓

fw3d's profile picture

Fred Moon 🚀

3,086 subscribers

73,875 views • 5 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could actually do. Meet GLM-X Preview On paper, a few things immediately stood out: → 1M context window → Agentic coding capabilities → Works inside Claude Code → Designed for large-scale coding and reasoning workflows But specs don't matter much if the model can't deliver in practice. So I gave it a real-world task. THE TEST One prompt: > Build a modern AI lead generation dashboard using React and Tailwind CSS. Requirements: → Dark mode → Analytics dashboard → Lead table → Email outreach section → Responsive design → Production-ready component structure Instead of generating a few snippets, it planned the architecture, generated the dashboard components, created the Tailwind configuration, and walked through the implementation requirements. What impressed me most wasn't the code itself. It was how well it maintained context throughout the workflow. That's where a 1M context window starts becoming useful. Less time re-explaining requirements. Less context loss. More room for complex projects. The AI coding race is getting very interesting. And it's no longer just GPT, Claude, and Gemini competing for attention. Results from my test below 👇
0:33

CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could actually do. Meet GLM-X Preview On paper, a few things immediately stood out: → 1M context window → Agentic coding capabilities → Works inside Claude Code → Designed for large-scale coding and reasoning workflows But specs don't matter much if the model can't deliver in practice. So I gave it a real-world task. THE TEST One prompt: > Build a modern AI lead generation dashboard using React and Tailwind CSS. Requirements: → Dark mode → Analytics dashboard → Lead table → Email outreach section → Responsive design → Production-ready component structure Instead of generating a few snippets, it planned the architecture, generated the dashboard components, created the Tailwind configuration, and walked through the implementation requirements. What impressed me most wasn't the code itself. It was how well it maintained context throughout the workflow. That's where a 1M context window starts becoming useful. Less time re-explaining requirements. Less context loss. More room for complex projects. The AI coding race is getting very interesting. And it's no longer just GPT, Claude, and Gemini competing for attention. Results from my test below 👇

Md Riyazuddin

31,199 views • 27 days ago

I just built a Claude skill that acts as a second brain for DTC brands 🤯 Drop your ad exports, customer reviews, competitor screenshots, and brand docs into a folder → Claude compiles it all into an organized wiki you can ask questions against. All inside Claude Cowork. Perfect for DTC brands and agencies whose knowledge is scattered across Google Drive, Notion, Meta Ads Manager, Figma, and 47 spreadsheets nobody has opened in 3 months. If every strategic question takes 2 hours to answer because the data lives in 8 different places ... This skill eliminates the entire loop: → Claude scaffolds a DTC folder structure: ads, customers, competitors, brand, performance, notes → You drop every file you have into those folders — messy, unorganized, exactly how you have them now → Claude reads everything and compiles a wiki: hooks-that-work, customer-pains, competitor-angles, brand-voice, performance-patterns, creative-brief-library → Every article is cross-linked and traceable back to the source file → You ask questions against the wiki — "what hooks are actually working?" "what objections come up most?" "where are my competitors weak?" → Claude answers, grounded entirely in your own data → Save the answers back in and the system gets smarter every time you use it No more hunting through 12 tools. No more "where did I save that brief?" No more answering the same question twice. What you get: → A complete DTC brand brain scaffold in 60 seconds → Six core wiki articles Claude populates automatically from your raw files → A schema file that tells Claude exactly how to maintain the wiki for DTC use cases → Monthly health checks that catch contradictions and flag gaps before errors compound → A knowledge base that compounds — every question you ask makes the next answer better Built on a methodology Andrej Karpathy shared for personal knowledge bases, I rebuilt the entire thing for DTC operators: folder structure, schema rules, wiki articles, and question frameworks all tuned for brands and agencies. I put together the full skill file plus a playbook walking through the exact setup and 5 real questions to ask your brand brain. Want it for free? > Like this post > Comment "BRAIN" And I'll send it over (must be following so I can DM)
0:35

I just built a Claude skill that acts as a second brain for DTC brands 🤯 Drop your ad exports, customer reviews, competitor screenshots, and brand docs into a folder → Claude compiles it all into an organized wiki you can ask questions against. All inside Claude Cowork. Perfect for DTC brands and agencies whose knowledge is scattered across Google Drive, Notion, Meta Ads Manager, Figma, and 47 spreadsheets nobody has opened in 3 months. If every strategic question takes 2 hours to answer because the data lives in 8 different places ... This skill eliminates the entire loop: → Claude scaffolds a DTC folder structure: ads, customers, competitors, brand, performance, notes → You drop every file you have into those folders — messy, unorganized, exactly how you have them now → Claude reads everything and compiles a wiki: hooks-that-work, customer-pains, competitor-angles, brand-voice, performance-patterns, creative-brief-library → Every article is cross-linked and traceable back to the source file → You ask questions against the wiki — "what hooks are actually working?" "what objections come up most?" "where are my competitors weak?" → Claude answers, grounded entirely in your own data → Save the answers back in and the system gets smarter every time you use it No more hunting through 12 tools. No more "where did I save that brief?" No more answering the same question twice. What you get: → A complete DTC brand brain scaffold in 60 seconds → Six core wiki articles Claude populates automatically from your raw files → A schema file that tells Claude exactly how to maintain the wiki for DTC use cases → Monthly health checks that catch contradictions and flag gaps before errors compound → A knowledge base that compounds — every question you ask makes the next answer better Built on a methodology Andrej Karpathy shared for personal knowledge bases, I rebuilt the entire thing for DTC operators: folder structure, schema rules, wiki articles, and question frameworks all tuned for brands and agencies. I put together the full skill file plus a playbook walking through the exact setup and 5 real questions to ask your brand brain. Want it for free? > Like this post > Comment "BRAIN" And I'll send it over (must be following so I can DM)

Mike Futia

15,158 views • 3 months ago

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.
1:19

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

Steve (Builder.io)

123,405 views • 28 days ago

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!
0:53

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Akshay 🚀

85,740 views • 2 months ago

Here's what the Founder of Claude Code does before he starts ANY project: 1. Plans first, codes never, he goes back and forth with Claude on the plan until it's perfect. No code gets written yet 2. Creates a CLAUDE.md file (a simple doc that Claude reads every session so it knows your project, your rules, your style) 3. Gives Claude a way to verify its own work - For backend: write and run tests - For UI: take screenshots, check in browser Claude should never finish a task without proving it works 4. Sets up project-level permission rules in settings.json instead of skipping permissions entirely. Shared with the whole team 5. Five more preparation steps in VIDEO BELOW 6. Only then switches to auto-accept mode and lets Claude build The part most people miss: he doesn't treat Claude as a magic box that gets things right first try he treats it like a junior dev that needs clear instructions, feedback loops, and guardrails at scale he runs multiple sessions in parallel, uses Opus with thinking enabled because it makes fewer mistakes even though it's slower and relies on background agents that push code for later review his setup is surprisingly simple. no crazy custom tools. just slash commands, subagents, and a clean CLAUDE.md the difference isn't the tool. it's how you set it up before you start ❤️ P.S. for sure 99.5% of readers will scroll down this tweet, but I send it to 0.5% who loves to learn how to improve your workflow daily and control 99.5% in 2 years Hard skills literally mean nothing in our world The most important skills which you can have are: building architectures and orchestrations If you master it and use a creative approach, CONGRATS
9:54

Here's what the Founder of Claude Code does before he starts ANY project: 1. Plans first, codes never, he goes back and forth with Claude on the plan until it's perfect. No code gets written yet 2. Creates a CLAUDE.md file (a simple doc that Claude reads every session so it knows your project, your rules, your style) 3. Gives Claude a way to verify its own work - For backend: write and run tests - For UI: take screenshots, check in browser Claude should never finish a task without proving it works 4. Sets up project-level permission rules in settings.json instead of skipping permissions entirely. Shared with the whole team 5. Five more preparation steps in VIDEO BELOW 6. Only then switches to auto-accept mode and lets Claude build The part most people miss: he doesn't treat Claude as a magic box that gets things right first try he treats it like a junior dev that needs clear instructions, feedback loops, and guardrails at scale he runs multiple sessions in parallel, uses Opus with thinking enabled because it makes fewer mistakes even though it's slower and relies on background agents that push code for later review his setup is surprisingly simple. no crazy custom tools. just slash commands, subagents, and a clean CLAUDE.md the difference isn't the tool. it's how you set it up before you start ❤️ P.S. for sure 99.5% of readers will scroll down this tweet, but I send it to 0.5% who loves to learn how to improve your workflow daily and control 99.5% in 2 years Hard skills literally mean nothing in our world The most important skills which you can have are: building architectures and orchestrations If you master it and use a creative approach, CONGRATS

Ronin

146,503 views • 2 months ago

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:
1:21

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

42,501 views • 21 days ago

There's so much focus on "how can AI do my work for me?" I think the more important question is "what work can I now do with AI that I would have never attempted before?" Earlier this year I wrote freestiler, a vector tiling engine for R and Python, with the help of Claude and Codex. I knew what the ideal engine looked like and how it would work at a high level. I didn't know how to put it together, and I don't know Rust, the language I wanted under the hood. Previously I would never have attempted this project as the ROI wasn't there. It would have taken me a year or more to learn the internals of a vector tiling engine and enough Rust to implement one. With Opus-level models, I could take it on. freestiler now powers all my vector tiling pipelines, including the map below rendering 143 million jobs from LODES, and it has 114 GitHub stars. Building this way has required a different set of skills. I don't review the code line by line. I set up adversarial agents to do that and write the test suites. What I review is the architecture, the behavior, and the results. Agent teams surface findings and explain their reasoning; I evaluate and critique. My job isn't to stress over code formatting, but instead to focus on questions like whether the engine is designed right, whether the output is correct, and if the UX makes sense. This means that I haven't "replaced my work." I've taken on entirely new work, with the help of agents, that I would have never done otherwise. It has taken some getting used to shipping code I haven't personally typed. In the old way of working, I built understanding through writing that code. Now I build understanding through managing the project - writing a spec, reviewing structure, evaluating UX. And that's helped me think a whole lot bigger in terms of what I can now do.
1:00

There's so much focus on "how can AI do my work for me?" I think the more important question is "what work can I now do with AI that I would have never attempted before?" Earlier this year I wrote freestiler, a vector tiling engine for R and Python, with the help of Claude and Codex. I knew what the ideal engine looked like and how it would work at a high level. I didn't know how to put it together, and I don't know Rust, the language I wanted under the hood. Previously I would never have attempted this project as the ROI wasn't there. It would have taken me a year or more to learn the internals of a vector tiling engine and enough Rust to implement one. With Opus-level models, I could take it on. freestiler now powers all my vector tiling pipelines, including the map below rendering 143 million jobs from LODES, and it has 114 GitHub stars. Building this way has required a different set of skills. I don't review the code line by line. I set up adversarial agents to do that and write the test suites. What I review is the architecture, the behavior, and the results. Agent teams surface findings and explain their reasoning; I evaluate and critique. My job isn't to stress over code formatting, but instead to focus on questions like whether the engine is designed right, whether the output is correct, and if the UX makes sense. This means that I haven't "replaced my work." I've taken on entirely new work, with the help of agents, that I would have never done otherwise. It has taken some getting used to shipping code I haven't personally typed. In the old way of working, I built understanding through writing that code. Now I build understanding through managing the project - writing a spec, reviewing structure, evaluating UX. And that's helped me think a whole lot bigger in terms of what I can now do.

Kyle Walker

13,396 views • 6 days ago

Claude Code can ship a 45-second animated explainer ad in 30 minutes. No video editor needed, just CC + skills. Here's how I made this video for Soteri Skin 👇 1. /plan Concept Brief (Claude Code) I handwrite a concept brief, then chat with the agent to iterate on it. The agent gathers any raw materials we might need - context about the brand, product images, end card, etc. The concept brief details the concept, characters, visual style, script, etc 2. /prepare a moodboard (CC + GPT Image 2 + ElevenLabs) After reviewing the script, generate: - character reference images - voiceover samples for the characters / narrator - the storyboard (scene by scene grid) - a few keyframe scenes 3. /generate Keyframes for each scene (CC uses Nano Banana or GPT Image 2) Uses the character references from the previous step to generate keyframes for each scene. I probably should have done a round of iteration at this step – there's some character drift and the pH meter representation could have been better. 4. /animate Keyframe → Animated Clip (CC uses Fal Seedance) Generate 2-4 representative scenes first to see a preview. If it looks good, then generate everything. 5. /stitch (CC + ffmpeg + ElevenLabs) - Stitch clips together with hard cut - Add a music score + SFX - Sync clips to the VO - Add captions - Review and edit timing / pacing issues 6. /watch the final cut and review it - as a video editor for technical errors (mismatched voiceover and visuals, AI hallucinations, etc) - as a viewer (ICP). I delegate most of the review to the agent because it catches more things and keeps me out of the loop as much as possible. It also fixes any issues found in the review. That's it. This video took me 30 minutes because I have already created skills for everything I described above. Some day, this will be < 5 minutes. I just review and chat to provide direction and feedback. The skills do all the technical work. 7. /learn Extracts learnings and updates the skills. This final step is really important. It turns this process into a closed loop system that makes the next video much easier to create because all the learnings from the human-in-the-loop process get encoded into code. Skills are code too. If you want access to the skill, drop a comment, and I'll DM it to you (must be following). If you want to make AI video ads like this, DM me.
0:45

Claude Code can ship a 45-second animated explainer ad in 30 minutes. No video editor needed, just CC + skills. Here's how I made this video for Soteri Skin 👇 1. /plan Concept Brief (Claude Code) I handwrite a concept brief, then chat with the agent to iterate on it. The agent gathers any raw materials we might need - context about the brand, product images, end card, etc. The concept brief details the concept, characters, visual style, script, etc 2. /prepare a moodboard (CC + GPT Image 2 + ElevenLabs) After reviewing the script, generate: - character reference images - voiceover samples for the characters / narrator - the storyboard (scene by scene grid) - a few keyframe scenes 3. /generate Keyframes for each scene (CC uses Nano Banana or GPT Image 2) Uses the character references from the previous step to generate keyframes for each scene. I probably should have done a round of iteration at this step – there's some character drift and the pH meter representation could have been better. 4. /animate Keyframe → Animated Clip (CC uses Fal Seedance) Generate 2-4 representative scenes first to see a preview. If it looks good, then generate everything. 5. /stitch (CC + ffmpeg + ElevenLabs) - Stitch clips together with hard cut - Add a music score + SFX - Sync clips to the VO - Add captions - Review and edit timing / pacing issues 6. /watch the final cut and review it - as a video editor for technical errors (mismatched voiceover and visuals, AI hallucinations, etc) - as a viewer (ICP). I delegate most of the review to the agent because it catches more things and keeps me out of the loop as much as possible. It also fixes any issues found in the review. That's it. This video took me 30 minutes because I have already created skills for everything I described above. Some day, this will be < 5 minutes. I just review and chat to provide direction and feedback. The skills do all the technical work. 7. /learn Extracts learnings and updates the skills. This final step is really important. It turns this process into a closed loop system that makes the next video much easier to create because all the learnings from the human-in-the-loop process get encoded into code. Skills are code too. If you want access to the skill, drop a comment, and I'll DM it to you (must be following). If you want to make AI video ads like this, DM me.

Shiv

11,608 views • 1 month ago

If you watch this ~50 minute screen recording closely (yeah, I know, it's long; there are also some times when my computer was very slow and laggy, just skip past that part. And at one point I had to run and get my 9-month-old a new bottle and left it on a boring screen, sorry!), I believe you can see real signs of the kind of runaway, recursive AI self-improvement that people have been warning of for a while (Mr. Kurzweil most notably and prophetically). Why do I say that? What's different now? Well, there's a reason my set of agent coding tooling is called the Flywheel. These tools all mutually self-reinforce each other. And they all flow directly into my ntm tool (short for "named_tmux_manager"), which acts as a sort of integration point and nerve center for the tools (this is becoming more true by the minute as I'm now seriously working on ntm). Now, ntm was something I started making to automate some aspects of my workflow, but it was the kind of thing where, until it was perfect, it sort of just slowed me down. So I didn't actually use it even though I kept working on it and trying to improve it, and suggested to users that they try it in my tutorials. Well anyway, I finally got around to "dogfooding" ntm last night, and now it's going to get very dramatically better at an alarming rate. Some of that is from applying my "idea wizard" prompt to generate more useful features and building that stuff out and addressing obvious pain points I encountered during my newfound usage of the tool. But a lot comes from my realization that, once again, ntm's true utility is not as a tool for ME, but for an agent. That is, ntm lets one instance of Claude Code or Codex act as, well, me, do the things that I had been doing manually. Do I wish I had started using ntm earlier? No, for two big reasons: 1) Doing it manually helped me build up my intuition massively, which directly led me down the path of creating useful prompt strategies and workflows; these often began as ad-hoc prompts that I realized could be generalized and made more versatile/universal. Lesson: don't prematurely automate until you have an intimate, intuitive feel for your "core value-add loop." Otherwise you'll have a fully automated system quickly that efficiently and automatically does a stupid or otherwise sub-optimal thing. 2) My eyes have been opened to the beauty and power of Skills. I'm not talking about your garden-variety skills that are just a simple markdown file. I'm talking about true tour-de-force directories of perfectly structured and organized files that are filled with good information, insights, workflows, etc., but presented in a way that is highly optimized for consumption by AI agents, with extreme attention paid to things like perfect progressive disclosure, token density, agent-ergonomics, agent-intuitiveness, etc. And also Skills that go way beyond markdown files, with full integration into Claude Code where it makes sense via hooks, sub-agents, and even Python scripts. These kinds of skills are a qualitative difference in expressive power and usefulness and a total game changer. They are also effectively composable, creating almost an algebra of skills that let you use them together in powerful ways. I'm working on a subscription service website and CLI tool now to share what I've learned here most effectively, stay tuned for that in the coming days. Anyway, I now know what to make and how to make it. So, getting back to that screen recording, what does it show that makes me claim recursive self-improvement is here? If you keep your eye on the upper left tmux pane, that's the "controller" agent. It is using ntm to control all the other panes which are also running Claude Code (but ntm fully supports other agent types like Codex and Gemini-CLI, and it's trivially easy to mix and match them if you wanted to have, say, 8 CCs and 6 Codexes for writing the code and 3 Gemini-CLIs for reviewing code.) Now, there's nothing that crazy about this much so far. But where it starts to get very cool is that as the session continues and we encounter real-world problems, things like my ridiculously overloaded computer that keeps hanging for long periods, Claude Code instances that crash and get into a frozen, unresponsive state, it can learn from that. And you can see it using my skill writing skill to refine its ntm vibe coding skill in real time. And then take that skill and refine it to be more intuitive for itself. Or use my cass tool skill to search all the session histories to look for problems that came up and strategize how to solve them. The most useful part was when, towards the end of the session, I told it to reflect on all the things we had done and problems we encountered. One way it can usefully leverage those reflections is by improving its ntm vibe coding skill to make it cover more edge cases and exigencies. But the other, more fundamental, way is for it to conceive of and design the optimal new features and functionality for ntm itself so that the tool embodies those lessons in a first-class way. This offloads cognition from its brain onto its tooling, just like how a person can lean on spellcheck or a calculator. It codifies correct, effective reasoning at the tool level, where it's more reliable and robust and repeatable. And btw, did you notice what code base it was working on the whole time? It was none other than ntm itself! So as it worked on its own tool, it had reflections and ideas about how to further improve the tool. Now, it could have just as easily gotten those insights and ideas while using ntm to work on a different project, but the fact that it was working on itself is almost gloriously meta and recursive. So by the end, after learning from tending to a big group of agent workers (btw, I have previously emphasized doing everything in a really distributed/decentralized way, where each fungible agent gets identical marching orders that tell it to use my bv tool to find the optimal bead to work on. This does work very well, but occasionally results in some contention and overlap from thundering herd, or at least wastes time/tokens/communication in avoiding that before the agents waste time duplicating work. But in this new ntm-oriented workflow, I was able to have the controller agent in the upper left use bv itself and then optimally parcel out the instructions to each agent so that we could know for sure that there's no overlap), I ended up with a ton of new beads for new features, which I had it optimize and polish a few times. Now I can swap to a new Claude Max account and have the swarm implement all those new features! It should only take a couple passes like the one shown in the screen recording to get everything implemented. Then we can rinse and repeat, having the agent read through the full session histories of each agent and its experience from its own session in sending ntm commands and seeing how they worked out in practice, to come up with the next batch of changes to both its ntm vibe coding skill AND to the ntm tool itself. Do you see how rapidly this turns into Skynet? My mistake earlier was in focusing on making myself a "faster horse" as Henry Ford used to joke about customers wanting before he showed them what they should really want (a Model T). That is, something that would make my experience nicer while doing this agent swarm based development workflow. But the obvious lesson is that you should make all your tooling agent-first because the agents are just better at this stuff. You can still watch, and of course I did add a ridiculous number of very nice human-centric features to ntm that you'll be seeing in the next day or two, but those are really kind of "for fun" to make us humans feel better about the process. All the real value-add is happening "by agents, for agents." PS: Towards the end, you can see me switch to my Mac and tell Claude to improve the skill that I made earlier today for taking the mkv screen recording files from OBS Studio and muxing them into MP4 files for sharing, while downloading songs from YouTube to serve as the background music. I made it so it can also grab the thumbnails and generate little song credit cards that show up in the lower right corner. This worked perfectly the first time! I'll include some screenshots in a response post showing how that worked, but it was awesome to witness. Skills are POWERFUL. I'll also post a link to this video on YouTube if you prefer to watch it there.
51:48

If you watch this ~50 minute screen recording closely (yeah, I know, it's long; there are also some times when my computer was very slow and laggy, just skip past that part. And at one point I had to run and get my 9-month-old a new bottle and left it on a boring screen, sorry!), I believe you can see real signs of the kind of runaway, recursive AI self-improvement that people have been warning of for a while (Mr. Kurzweil most notably and prophetically). Why do I say that? What's different now? Well, there's a reason my set of agent coding tooling is called the Flywheel. These tools all mutually self-reinforce each other. And they all flow directly into my ntm tool (short for "named_tmux_manager"), which acts as a sort of integration point and nerve center for the tools (this is becoming more true by the minute as I'm now seriously working on ntm). Now, ntm was something I started making to automate some aspects of my workflow, but it was the kind of thing where, until it was perfect, it sort of just slowed me down. So I didn't actually use it even though I kept working on it and trying to improve it, and suggested to users that they try it in my tutorials. Well anyway, I finally got around to "dogfooding" ntm last night, and now it's going to get very dramatically better at an alarming rate. Some of that is from applying my "idea wizard" prompt to generate more useful features and building that stuff out and addressing obvious pain points I encountered during my newfound usage of the tool. But a lot comes from my realization that, once again, ntm's true utility is not as a tool for ME, but for an agent. That is, ntm lets one instance of Claude Code or Codex act as, well, me, do the things that I had been doing manually. Do I wish I had started using ntm earlier? No, for two big reasons: 1) Doing it manually helped me build up my intuition massively, which directly led me down the path of creating useful prompt strategies and workflows; these often began as ad-hoc prompts that I realized could be generalized and made more versatile/universal. Lesson: don't prematurely automate until you have an intimate, intuitive feel for your "core value-add loop." Otherwise you'll have a fully automated system quickly that efficiently and automatically does a stupid or otherwise sub-optimal thing. 2) My eyes have been opened to the beauty and power of Skills. I'm not talking about your garden-variety skills that are just a simple markdown file. I'm talking about true tour-de-force directories of perfectly structured and organized files that are filled with good information, insights, workflows, etc., but presented in a way that is highly optimized for consumption by AI agents, with extreme attention paid to things like perfect progressive disclosure, token density, agent-ergonomics, agent-intuitiveness, etc. And also Skills that go way beyond markdown files, with full integration into Claude Code where it makes sense via hooks, sub-agents, and even Python scripts. These kinds of skills are a qualitative difference in expressive power and usefulness and a total game changer. They are also effectively composable, creating almost an algebra of skills that let you use them together in powerful ways. I'm working on a subscription service website and CLI tool now to share what I've learned here most effectively, stay tuned for that in the coming days. Anyway, I now know what to make and how to make it. So, getting back to that screen recording, what does it show that makes me claim recursive self-improvement is here? If you keep your eye on the upper left tmux pane, that's the "controller" agent. It is using ntm to control all the other panes which are also running Claude Code (but ntm fully supports other agent types like Codex and Gemini-CLI, and it's trivially easy to mix and match them if you wanted to have, say, 8 CCs and 6 Codexes for writing the code and 3 Gemini-CLIs for reviewing code.) Now, there's nothing that crazy about this much so far. But where it starts to get very cool is that as the session continues and we encounter real-world problems, things like my ridiculously overloaded computer that keeps hanging for long periods, Claude Code instances that crash and get into a frozen, unresponsive state, it can learn from that. And you can see it using my skill writing skill to refine its ntm vibe coding skill in real time. And then take that skill and refine it to be more intuitive for itself. Or use my cass tool skill to search all the session histories to look for problems that came up and strategize how to solve them. The most useful part was when, towards the end of the session, I told it to reflect on all the things we had done and problems we encountered. One way it can usefully leverage those reflections is by improving its ntm vibe coding skill to make it cover more edge cases and exigencies. But the other, more fundamental, way is for it to conceive of and design the optimal new features and functionality for ntm itself so that the tool embodies those lessons in a first-class way. This offloads cognition from its brain onto its tooling, just like how a person can lean on spellcheck or a calculator. It codifies correct, effective reasoning at the tool level, where it's more reliable and robust and repeatable. And btw, did you notice what code base it was working on the whole time? It was none other than ntm itself! So as it worked on its own tool, it had reflections and ideas about how to further improve the tool. Now, it could have just as easily gotten those insights and ideas while using ntm to work on a different project, but the fact that it was working on itself is almost gloriously meta and recursive. So by the end, after learning from tending to a big group of agent workers (btw, I have previously emphasized doing everything in a really distributed/decentralized way, where each fungible agent gets identical marching orders that tell it to use my bv tool to find the optimal bead to work on. This does work very well, but occasionally results in some contention and overlap from thundering herd, or at least wastes time/tokens/communication in avoiding that before the agents waste time duplicating work. But in this new ntm-oriented workflow, I was able to have the controller agent in the upper left use bv itself and then optimally parcel out the instructions to each agent so that we could know for sure that there's no overlap), I ended up with a ton of new beads for new features, which I had it optimize and polish a few times. Now I can swap to a new Claude Max account and have the swarm implement all those new features! It should only take a couple passes like the one shown in the screen recording to get everything implemented. Then we can rinse and repeat, having the agent read through the full session histories of each agent and its experience from its own session in sending ntm commands and seeing how they worked out in practice, to come up with the next batch of changes to both its ntm vibe coding skill AND to the ntm tool itself. Do you see how rapidly this turns into Skynet? My mistake earlier was in focusing on making myself a "faster horse" as Henry Ford used to joke about customers wanting before he showed them what they should really want (a Model T). That is, something that would make my experience nicer while doing this agent swarm based development workflow. But the obvious lesson is that you should make all your tooling agent-first because the agents are just better at this stuff. You can still watch, and of course I did add a ridiculous number of very nice human-centric features to ntm that you'll be seeing in the next day or two, but those are really kind of "for fun" to make us humans feel better about the process. All the real value-add is happening "by agents, for agents." PS: Towards the end, you can see me switch to my Mac and tell Claude to improve the skill that I made earlier today for taking the mkv screen recording files from OBS Studio and muxing them into MP4 files for sharing, while downloading songs from YouTube to serve as the background music. I made it so it can also grab the thumbnails and generate little song credit cards that show up in the lower right corner. This worked perfectly the first time! I'll include some screenshots in a response post showing how that worked, but it was awesome to witness. Skills are POWERFUL. I'll also post a link to this video on YouTube if you prefer to watch it there.

Jeffrey Emanuel

25,483 views • 5 months ago

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.
0:22

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

Akshay 🚀

118,124 views • 1 month ago

10 free Google AI tools nobody talks about. while everyone's burning $20/mo on chatgpt and claude, google quietly shipped a stack worth $200+/mo. all free. all yours. — 1️⃣ NotebookLM — your second brain upload sources (PDFs, websites, audio, YouTube). it summarizes, builds mind maps, generates quizzes, drafts slide decks, even turns your notes into a podcast you can listen to on a walk. free tier: 100 notebooks, 50 sources each, 50 chats/day, 3 audio overviews/day. replaces: notion AI + perplexity + readwise — 2️⃣ Google AI Studio — the free gemini playground web playground for gemini 3 pro and flash with a free API key. generous limits. paste a 1M-token context window and watch it actually use it. faster than the openai playground and free where openai charges per token. replaces: openai playground + paid API credits — 3️⃣ Gemini CLI — google's open-source terminal agent apache 2.0 licensed. one command (npx @google/gemini-cli) and you've got an agent in your terminal that reads your codebase, runs shell commands, and ships PRs. drop-in claude code alternative. replaces: claude code ($20/mo by default) — 4️⃣ Jules — async coding agent assign jules a github issue. it spins up a cloud VM, clones your repo, writes the plan, makes the changes, opens a PR. free tier: 15 tasks/day, 3 concurrent, runs on gemini flash. replaces: devin ($20/mo+) + cursor agent 5️⃣ Stitch — text → UI → code google's free figma killer. describe an interface, get production-ready HTML/CSS/Tailwind + figma export. march 2026 update added voice canvas, infinite canvas, and MCP integration with cursor. 350 standard + 200 experimental generations/month free. replaces: galileo AI + early-stage figma work — 6️⃣ Gemma 4 — open-weight LLM google's flagship open model. apache 2.0. 2B, 4B, 26B-MoE, and 31B variants. 256K context. runs on ollama with one command. quantized versions run on a 4090 or beefy laptop. replaces: paying for hosted LLM inference — 7️⃣ Illuminate — papers → podcasts paste an arxiv preprint link. illuminate turns dense research papers into a 6-8 min conversation between two AI hosts breaking it down. perfect for commute reading you can't do at a desk. note: still in waitlist for some regions. replaces: snipd + manual research reading — 8️⃣ Learn About (LearnLM) — adaptive AI tutor drop in any topic you're stuck on. highlight a word, click "go deeper," and the interface adapts in real time to your comprehension level. visual explanations, follow-up questions, the works. replaces: paid tutoring on niche topics — 9️⃣ Google Labs FX (ImageFX + Flow + MusicFX) — free imagen, veo, musicLM google labs creative suite. text-to-image (imagen 4), text-to-video (veo via Flow), text-to-music (musicLM). free tier: limited daily generations. the heavy veo 3.1 features are paid (AI Pro $19.99/mo). still worth using for image and music — those stay free. replaces: midjourney + suno (free tier only — runway-level video gen is paid) — 🔟 Google Colab — free GPU notebooks free T4 GPU + 12GB RAM in a browser tab. enough to fine-tune small models, run stable diffusion, prototype agents. the launching pad for half the ML projects on github. replaces: paid cloud GPU rentals — a quick honest note: these tools aren't 1:1 better than the paid versions they replace. but they're decent enough to get most things done — especially if you're not a heavy user or you've got little funds to play with. i've put all 10 in a public github repo (link in comments). follow + turn on post notifications for more useful posts like this 🔔
0:34

10 free Google AI tools nobody talks about. while everyone's burning $20/mo on chatgpt and claude, google quietly shipped a stack worth $200+/mo. all free. all yours. — 1️⃣ NotebookLM — your second brain upload sources (PDFs, websites, audio, YouTube). it summarizes, builds mind maps, generates quizzes, drafts slide decks, even turns your notes into a podcast you can listen to on a walk. free tier: 100 notebooks, 50 sources each, 50 chats/day, 3 audio overviews/day. replaces: notion AI + perplexity + readwise — 2️⃣ Google AI Studio — the free gemini playground web playground for gemini 3 pro and flash with a free API key. generous limits. paste a 1M-token context window and watch it actually use it. faster than the openai playground and free where openai charges per token. replaces: openai playground + paid API credits — 3️⃣ Gemini CLI — google's open-source terminal agent apache 2.0 licensed. one command (npx @google/gemini-cli) and you've got an agent in your terminal that reads your codebase, runs shell commands, and ships PRs. drop-in claude code alternative. replaces: claude code ($20/mo by default) — 4️⃣ Jules — async coding agent assign jules a github issue. it spins up a cloud VM, clones your repo, writes the plan, makes the changes, opens a PR. free tier: 15 tasks/day, 3 concurrent, runs on gemini flash. replaces: devin ($20/mo+) + cursor agent 5️⃣ Stitch — text → UI → code google's free figma killer. describe an interface, get production-ready HTML/CSS/Tailwind + figma export. march 2026 update added voice canvas, infinite canvas, and MCP integration with cursor. 350 standard + 200 experimental generations/month free. replaces: galileo AI + early-stage figma work — 6️⃣ Gemma 4 — open-weight LLM google's flagship open model. apache 2.0. 2B, 4B, 26B-MoE, and 31B variants. 256K context. runs on ollama with one command. quantized versions run on a 4090 or beefy laptop. replaces: paying for hosted LLM inference — 7️⃣ Illuminate — papers → podcasts paste an arxiv preprint link. illuminate turns dense research papers into a 6-8 min conversation between two AI hosts breaking it down. perfect for commute reading you can't do at a desk. note: still in waitlist for some regions. replaces: snipd + manual research reading — 8️⃣ Learn About (LearnLM) — adaptive AI tutor drop in any topic you're stuck on. highlight a word, click "go deeper," and the interface adapts in real time to your comprehension level. visual explanations, follow-up questions, the works. replaces: paid tutoring on niche topics — 9️⃣ Google Labs FX (ImageFX + Flow + MusicFX) — free imagen, veo, musicLM google labs creative suite. text-to-image (imagen 4), text-to-video (veo via Flow), text-to-music (musicLM). free tier: limited daily generations. the heavy veo 3.1 features are paid (AI Pro $19.99/mo). still worth using for image and music — those stay free. replaces: midjourney + suno (free tier only — runway-level video gen is paid) — 🔟 Google Colab — free GPU notebooks free T4 GPU + 12GB RAM in a browser tab. enough to fine-tune small models, run stable diffusion, prototype agents. the launching pad for half the ML projects on github. replaces: paid cloud GPU rentals — a quick honest note: these tools aren't 1:1 better than the paid versions they replace. but they're decent enough to get most things done — especially if you're not a heavy user or you've got little funds to play with. i've put all 10 in a public github repo (link in comments). follow + turn on post notifications for more useful posts like this 🔔

m0h

11,673 views • 1 month ago

CANCEL Your Weekend Plans, & Learn Claude Code Today. This Claude Code teaches more about vibe-coding in 30 mins than most tutorials do in hours. Save this, it'll change how you build forever People are building entire apps and charging clients $5,000 to $20,000 using Claude Code. This Claude Code video is a goldmine. Full Claude Code tutorial. Beginner to pro. Every feature. Every setup step. Every best practice. Zero prior knowledge needed. Save it. Watch it tonight. Not tomorrow. Tonight. Follow Himanshu Kumar so you don't miss the breakdowns for each feature. This is your complete Claude Code roadmap. Lose it and you lose the next 12 months of income. ↓ 1. Understand What Claude Code Actually Is. You think Claude Code is just another chatbot. It's not. And that misunderstanding is why you're broke. ChatGPT gives you text. Claude Code gives you software. It runs in your terminal. It reads your entire codebase. It writes files directly to your project. It runs commands on your machine. It debugs errors autonomously. It builds features end to end. You're not chatting. You're deploying a developer. One that works 24/7. Never asks for a raise. Never calls in sick. Never pushes broken code at 5 PM on a Friday. People are charging clients $5,000-$10,000 for apps they built with Claude Code in 3 hours. And you didn't even know this tool existed because you're still asking ChatGPT to write you a to-do list. The gap between you and people making money with AI isn't intelligence. It's awareness. Now you're aware. Save this post. Follow Himanshu Kumar for the complete breakdown of every Claude Code feature. ↓ 2. Set Up Claude Code Properly. Most people quit here. "It's too complicated." "I don't know terminal." "I'll set it up later." Later never comes. And "complicated" means "I watched for 30 seconds and gave up." The setup takes 10 minutes. Install Node.js. Install Claude Code via npm. Authenticate your account. Open your terminal. Done. 10 minutes. You spent longer this morning deciding what to have for breakfast. The video walks through every single click. Every command. Every screen. Assuming you know absolutely nothing. If you can download an app on your phone, you can set up Claude Code. It's the same level of difficulty. But you'll still tell yourself it's "too technical" because that excuse is more comfortable than admitting you're just scared to try something new. This is the setup that everything else builds on. Skip it and nothing works. ↓ 3. Use the Desktop App. You don't even need to live in the terminal if you don't want to. Claude Code has a desktop app. Clean interface. Visual feedback. Everything you need without touching command line. But here's the thing most people don't know: The desktop app isn't just a pretty wrapper. It lets you manage projects visually. See file changes in real time. Switch between projects instantly. The people making money with Claude Code use the desktop app for client projects because it's faster to manage multiple builds simultaneously. You're still opening 14 browser tabs to organize one project. They open one app and everything's there. Efficiency isn't a personality trait. It's a tool choice. Save this post. Follow Himanshu Kumar for the desktop app workflow that handles 5 client projects at once. ↓ 4. Install the Right Dependencies. This is where beginners silently fail and blame the tool. Claude Code needs certain dependencies installed to work properly. Miss one and everything breaks. Then you go on Twitter and say "Claude Code doesn't work." It works fine. You just didn't read the setup guide. The video covers every dependency you need. What to install. How to install it. How to verify it's working. No guessing. No Stack Overflow rabbit holes at midnight. No "why isn't this working" for 3 hours. Watch the dependency section once. Follow every step. Never deal with setup issues again. You spent more time last week troubleshooting a printer than this takes. ↓ 5. Work Inside Your Code Editor. Claude Code integrates directly with your code editor. VS Code. Cursor. Whatever you use. It's not a separate window you alt-tab between. It's right there. In your workflow. You type a request. Claude writes the code. The code appears in your editor. You review it. Accept it. Done. No copy pasting between windows. No reformatting code that got mangled in transit. No "which version was the right one." It's like pair programming with someone who never gets distracted, never argues about naming conventions, and actually writes code that works on the first try. Your current coding process is: Google the problem, read 5 answers on Stack Overflow, copy the wrong one, debug for an hour, find the right one, paste it in, break something else, repeat. Claude Code's process is: describe what you want, get working code, move on with your life. Same hour. One method produces working software. The other produces frustration and a browser history full of Stack Overflow tabs. Stop coding the hard way. Save this post. Follow Himanshu Kumar for code editor setup guides and integration tips. ↓ 6. Master Basic Usage. Most people learn 5% of a tool and say they "know" it. You "know" Photoshop because you can crop an image. You "know" Excel because you can sum a column. You "know" Claude Code because you asked it one question. Basic usage means: How to give Claude Code context about your project. How to ask for changes to existing code. How to generate new files and features. How to review what Claude produces. How to iterate when the output isn't perfect. These basics are the foundation of everything. Skip them and every advanced feature feels confusing. Master them and every advanced feature feels obvious. The video breaks down each one with real examples. Not theory. Actual usage on actual projects. You've been using AI tools at 5% capacity and wondering why your results are 5% of what others get. Save this post. Follow Himanshu Kumar for daily Claude Code usage tips. ↓ 7. Learn Every Command. Claude Code has commands that most users never discover. Because most users type one message and expect magic. That's not how professionals use it. Professionals use specific commands that tell Claude Code exactly what to do, how to do it, and what constraints to follow. The difference between a beginner and someone making $10K/month with Claude Code is knowing which command to use and when. The video walks through every single one. Not just what they do. But when to use each one. And why one command is better than another for specific situations. You've been using Claude Code like a hammer. These commands turn it into a full toolbox. Stop treating a power tool like a blunt instrument. Save this post. Follow Himanshu Kumar for the command cheat sheet I use daily. ↓ 8. Understand Modes and Shortcuts. Speed matters. The person who builds an app in 2 hours charges $5,000. The person who builds the same app in 2 days charges $2,000. Same app. Same quality. Different speed. Different income. Claude Code has modes that change how it operates. And shortcuts that cut your workflow time in half. Most people don't know either exists. They use Claude Code in default mode for everything. Like driving a car in first gear on the highway. Technically it works. But everyone is passing you. The video shows you every mode. Every shortcut. Every time-saving trick that separates the people charging $2,000 per project from the people charging $10,000. Speed is money. Literally. Save this post. Follow Himanshu Kumar for the shortcuts that cut my build time by 60%. ↓ 9. Write a Proper Planning Prompt. This is the section that separates amateurs from professionals. And it's the section most people skip. A planning prompt tells Claude Code what you're building before you start building it. Architecture. File structure. Technologies. Features. Constraints. Edge cases. Without a planning prompt, Claude Code guesses. And guessing produces garbage. With a planning prompt, Claude Code executes a clear plan. And clear plans produce working software. The video shows you exactly how to write a planning prompt that makes Claude Code produce professional-grade output on the first try. "But I just want to start coding." That's why your code breaks every time. That's why you restart projects 4 times. That's why nothing you build ever gets finished. Because you refuse to plan. A 5-minute planning prompt saves you 5 hours of debugging. But you'd rather skip the 5 minutes and suffer through the 5 hours because patience isn't your thing. And that's exactly why you're not making money. Planning is the most underpaid skill in coding. And the most overpaid when you master it. Save this post. Follow Himanshu Kumar for the planning prompt templates I use for every client project. ↓ 10. Choose the Right Model. Claude Code lets you select different AI models. Not all models are the same. Not all tasks need the same model. Using the most powerful model for a simple task wastes credits. Using a basic model for a complex task wastes time. The video explains: Which model to use for quick fixes. Which model to use for complex architecture. Which model to use for debugging. Which model to use for code generation. Most people pick one model and use it for everything. That's like using a sledgehammer to hang a picture frame. Model selection is strategy. And strategy is money. The people making $10K/month with Claude Code are strategic about every credit they spend. You're burning through credits because you use the most expensive model to write a hello world. ↓ 11. Use Git and Version Control. If you're not using version control, you're one mistake away from losing everything. Claude Code integrates with Git. Every change tracked. Every version saved. Every mistake reversible. Without Git: Claude makes a change. It breaks something. You can't undo it. You start over. 3 hours wasted. With Git: Claude makes a change. It breaks something. You roll back in 5 seconds. Keep working. Version control isn't optional. It's insurance. And the people not using it are the same people who say "I lost my entire project" like it's something that just happens. It doesn't just happen. It happens because you didn't set up Git. The video walks through the entire Git integration. Save this post. Follow Himanshu Kumar for the Git workflow that's saved every project I've ever built. ↓ 12. Set Up Claude MD and Memory. This is the feature that makes Claude Code feel like a real team member instead of a stranger you explain everything to every time. ClaudeMD is a memory file. You tell Claude Code about your project once. It remembers forever. Coding style preferences. Project architecture decisions. Technology stack. File naming conventions. Business logic rules. Without ClaudeMD: Every new conversation starts from zero. You explain the same things repeatedly. Output is inconsistent. With ClaudeMD: Claude knows your project. Claude follows your rules. Claude produces consistent, professional code. The difference between a sloppy freelancer and a reliable agency is consistency. Claude. MD gives you consistency without the agency overhead. Most people don't set this up and wonder why Claude Code gives different answers every time. ↓ 13. Automate with Tasks. This is where Claude Code stops being a tool and starts being an employee. Tasks let you define repeating workflows. "Every time I push code, run tests." "Every time I create a new file, add boilerplate." "Every time I start a session, check for errors." Automated. Hands-free. Consistent. You're doing these things manually every single day. The same checks. The same steps. The same routine. Tasks do them automatically. So you can focus on the work that actually makes money. Every manual task you automate is time you get back. And time is the only thing you can never make more of. Save this post. Follow Himanshu Kumar for the task automation templates that run my entire workflow. ↓ 14. Explore Features Most People Never Touch. The video covers features that 95% of Claude Code users don't know exist. Because they watched a 3-minute TikTok about Claude Code and think they're experts now. They're not. They're using 5% of a tool that can do everything. The full tutorial goes deep into features that most tutorials skip because they're "too advanced." They're not too advanced. They're too valuable for lazy creators to bother explaining. This video explains all of them. Clearly. For beginners. The 5% of features you don't know about are the 5% that make people rich. ↓ Let's zoom out. I just broke down 14 sections of Claude Code. Setup and installation. Desktop app. Dependencies. Code editor integration. Basic usage. Commands. Modes and shortcuts. Planning prompts. Model selection. Git and version control. Memory and Claude. MD. Tasks and automation. Advanced features. All in one video. All free. All beginner friendly. The person who masters even half of these in the next 2 weeks will be in the top 1% of Claude Code users. The top 1% of Claude Code users are the ones charging $5,000-$10,000 per project and building them in a single afternoon. Everyone else is asking ChatGPT to fix their resume. Same tools. Same access. Completely different outcomes. Because one person treats AI like a toy. And the other treats it like a business. ↓ Here's the hard truth nobody wants to hear. You don't have a talent problem. You don't have an intelligence problem. You don't have a resources problem. You have an action problem. Everything I just listed has a free tutorial right here in the attached video. 33 minutes. That's it. 33 minutes to learn the tool that people are using to build $5,000-$20,000/month businesses. You spent more time today scrolling Twitter than it takes to watch this video. You spent more time this week watching Netflix than it takes to master Claude Code basics. You spent more time this month doing nothing than it would take to completely change your income. The information is free. The tool is accessible. The opportunity is here. The only thing missing is you caring enough to start. ↓ CANCEL your plans this week. This isn't optional anymore. The people learning Claude Code right now will be building apps for the people who didn't learn it. That's not a prediction. That's already happening. Companies are replacing $150/hour developers with one person and Claude Code. If you code: learn Claude Code or become half as valuable by next year. If you don't code: learn Claude Code or miss the biggest opportunity to start earning from tech without a CS degree. There's no path forward that doesn't include AI coding tools. None. You have one window. Right now. This week. ↓ Here's your action plan for the next 7 days: Day 1: Watch the full video. Install Claude Code. Set up dependencies. Day 2: Learn basic usage. Try 5 different commands. Day 3: Write your first planning prompt. Build a small project. Day 4: Set up Claude. MD. Configure your memory file. Day 5: Master modes and shortcuts. Build a second project faster. Day 6: Set up Git integration. Automate with tasks. Day 7: Build something real. A tool, an app, a website. Ship it. 7 days. One tool. One completely different skill set. One completely different income potential. Or 7 more days of scrolling Twitter watching other people build things while you "plan to start." Your call. ↓ This is the most important video you'll watch this year. 33 minutes. Complete Claude Code mastery. From zero to building real projects. Save this post. Come back to it every single day this week. Check off each section as you complete it. Follow Himanshu Kumarfor daily Claude Code breakdowns, advanced tutorials, and the exact workflows that are turning beginners into $10K/month builders. The only thing between you and $10K/month with Claude Code is this video and 7 days. Don't waste them. You Must Follow me Himanshu Kumar, so i can send you DM.
35:48

CANCEL Your Weekend Plans, & Learn Claude Code Today. This Claude Code teaches more about vibe-coding in 30 mins than most tutorials do in hours. Save this, it'll change how you build forever People are building entire apps and charging clients $5,000 to $20,000 using Claude Code. This Claude Code video is a goldmine. Full Claude Code tutorial. Beginner to pro. Every feature. Every setup step. Every best practice. Zero prior knowledge needed. Save it. Watch it tonight. Not tomorrow. Tonight. Follow Himanshu Kumar so you don't miss the breakdowns for each feature. This is your complete Claude Code roadmap. Lose it and you lose the next 12 months of income. ↓ 1. Understand What Claude Code Actually Is. You think Claude Code is just another chatbot. It's not. And that misunderstanding is why you're broke. ChatGPT gives you text. Claude Code gives you software. It runs in your terminal. It reads your entire codebase. It writes files directly to your project. It runs commands on your machine. It debugs errors autonomously. It builds features end to end. You're not chatting. You're deploying a developer. One that works 24/7. Never asks for a raise. Never calls in sick. Never pushes broken code at 5 PM on a Friday. People are charging clients $5,000-$10,000 for apps they built with Claude Code in 3 hours. And you didn't even know this tool existed because you're still asking ChatGPT to write you a to-do list. The gap between you and people making money with AI isn't intelligence. It's awareness. Now you're aware. Save this post. Follow Himanshu Kumar for the complete breakdown of every Claude Code feature. ↓ 2. Set Up Claude Code Properly. Most people quit here. "It's too complicated." "I don't know terminal." "I'll set it up later." Later never comes. And "complicated" means "I watched for 30 seconds and gave up." The setup takes 10 minutes. Install Node.js. Install Claude Code via npm. Authenticate your account. Open your terminal. Done. 10 minutes. You spent longer this morning deciding what to have for breakfast. The video walks through every single click. Every command. Every screen. Assuming you know absolutely nothing. If you can download an app on your phone, you can set up Claude Code. It's the same level of difficulty. But you'll still tell yourself it's "too technical" because that excuse is more comfortable than admitting you're just scared to try something new. This is the setup that everything else builds on. Skip it and nothing works. ↓ 3. Use the Desktop App. You don't even need to live in the terminal if you don't want to. Claude Code has a desktop app. Clean interface. Visual feedback. Everything you need without touching command line. But here's the thing most people don't know: The desktop app isn't just a pretty wrapper. It lets you manage projects visually. See file changes in real time. Switch between projects instantly. The people making money with Claude Code use the desktop app for client projects because it's faster to manage multiple builds simultaneously. You're still opening 14 browser tabs to organize one project. They open one app and everything's there. Efficiency isn't a personality trait. It's a tool choice. Save this post. Follow Himanshu Kumar for the desktop app workflow that handles 5 client projects at once. ↓ 4. Install the Right Dependencies. This is where beginners silently fail and blame the tool. Claude Code needs certain dependencies installed to work properly. Miss one and everything breaks. Then you go on Twitter and say "Claude Code doesn't work." It works fine. You just didn't read the setup guide. The video covers every dependency you need. What to install. How to install it. How to verify it's working. No guessing. No Stack Overflow rabbit holes at midnight. No "why isn't this working" for 3 hours. Watch the dependency section once. Follow every step. Never deal with setup issues again. You spent more time last week troubleshooting a printer than this takes. ↓ 5. Work Inside Your Code Editor. Claude Code integrates directly with your code editor. VS Code. Cursor. Whatever you use. It's not a separate window you alt-tab between. It's right there. In your workflow. You type a request. Claude writes the code. The code appears in your editor. You review it. Accept it. Done. No copy pasting between windows. No reformatting code that got mangled in transit. No "which version was the right one." It's like pair programming with someone who never gets distracted, never argues about naming conventions, and actually writes code that works on the first try. Your current coding process is: Google the problem, read 5 answers on Stack Overflow, copy the wrong one, debug for an hour, find the right one, paste it in, break something else, repeat. Claude Code's process is: describe what you want, get working code, move on with your life. Same hour. One method produces working software. The other produces frustration and a browser history full of Stack Overflow tabs. Stop coding the hard way. Save this post. Follow Himanshu Kumar for code editor setup guides and integration tips. ↓ 6. Master Basic Usage. Most people learn 5% of a tool and say they "know" it. You "know" Photoshop because you can crop an image. You "know" Excel because you can sum a column. You "know" Claude Code because you asked it one question. Basic usage means: How to give Claude Code context about your project. How to ask for changes to existing code. How to generate new files and features. How to review what Claude produces. How to iterate when the output isn't perfect. These basics are the foundation of everything. Skip them and every advanced feature feels confusing. Master them and every advanced feature feels obvious. The video breaks down each one with real examples. Not theory. Actual usage on actual projects. You've been using AI tools at 5% capacity and wondering why your results are 5% of what others get. Save this post. Follow Himanshu Kumar for daily Claude Code usage tips. ↓ 7. Learn Every Command. Claude Code has commands that most users never discover. Because most users type one message and expect magic. That's not how professionals use it. Professionals use specific commands that tell Claude Code exactly what to do, how to do it, and what constraints to follow. The difference between a beginner and someone making $10K/month with Claude Code is knowing which command to use and when. The video walks through every single one. Not just what they do. But when to use each one. And why one command is better than another for specific situations. You've been using Claude Code like a hammer. These commands turn it into a full toolbox. Stop treating a power tool like a blunt instrument. Save this post. Follow Himanshu Kumar for the command cheat sheet I use daily. ↓ 8. Understand Modes and Shortcuts. Speed matters. The person who builds an app in 2 hours charges $5,000. The person who builds the same app in 2 days charges $2,000. Same app. Same quality. Different speed. Different income. Claude Code has modes that change how it operates. And shortcuts that cut your workflow time in half. Most people don't know either exists. They use Claude Code in default mode for everything. Like driving a car in first gear on the highway. Technically it works. But everyone is passing you. The video shows you every mode. Every shortcut. Every time-saving trick that separates the people charging $2,000 per project from the people charging $10,000. Speed is money. Literally. Save this post. Follow Himanshu Kumar for the shortcuts that cut my build time by 60%. ↓ 9. Write a Proper Planning Prompt. This is the section that separates amateurs from professionals. And it's the section most people skip. A planning prompt tells Claude Code what you're building before you start building it. Architecture. File structure. Technologies. Features. Constraints. Edge cases. Without a planning prompt, Claude Code guesses. And guessing produces garbage. With a planning prompt, Claude Code executes a clear plan. And clear plans produce working software. The video shows you exactly how to write a planning prompt that makes Claude Code produce professional-grade output on the first try. "But I just want to start coding." That's why your code breaks every time. That's why you restart projects 4 times. That's why nothing you build ever gets finished. Because you refuse to plan. A 5-minute planning prompt saves you 5 hours of debugging. But you'd rather skip the 5 minutes and suffer through the 5 hours because patience isn't your thing. And that's exactly why you're not making money. Planning is the most underpaid skill in coding. And the most overpaid when you master it. Save this post. Follow Himanshu Kumar for the planning prompt templates I use for every client project. ↓ 10. Choose the Right Model. Claude Code lets you select different AI models. Not all models are the same. Not all tasks need the same model. Using the most powerful model for a simple task wastes credits. Using a basic model for a complex task wastes time. The video explains: Which model to use for quick fixes. Which model to use for complex architecture. Which model to use for debugging. Which model to use for code generation. Most people pick one model and use it for everything. That's like using a sledgehammer to hang a picture frame. Model selection is strategy. And strategy is money. The people making $10K/month with Claude Code are strategic about every credit they spend. You're burning through credits because you use the most expensive model to write a hello world. ↓ 11. Use Git and Version Control. If you're not using version control, you're one mistake away from losing everything. Claude Code integrates with Git. Every change tracked. Every version saved. Every mistake reversible. Without Git: Claude makes a change. It breaks something. You can't undo it. You start over. 3 hours wasted. With Git: Claude makes a change. It breaks something. You roll back in 5 seconds. Keep working. Version control isn't optional. It's insurance. And the people not using it are the same people who say "I lost my entire project" like it's something that just happens. It doesn't just happen. It happens because you didn't set up Git. The video walks through the entire Git integration. Save this post. Follow Himanshu Kumar for the Git workflow that's saved every project I've ever built. ↓ 12. Set Up Claude MD and Memory. This is the feature that makes Claude Code feel like a real team member instead of a stranger you explain everything to every time. ClaudeMD is a memory file. You tell Claude Code about your project once. It remembers forever. Coding style preferences. Project architecture decisions. Technology stack. File naming conventions. Business logic rules. Without ClaudeMD: Every new conversation starts from zero. You explain the same things repeatedly. Output is inconsistent. With ClaudeMD: Claude knows your project. Claude follows your rules. Claude produces consistent, professional code. The difference between a sloppy freelancer and a reliable agency is consistency. Claude. MD gives you consistency without the agency overhead. Most people don't set this up and wonder why Claude Code gives different answers every time. ↓ 13. Automate with Tasks. This is where Claude Code stops being a tool and starts being an employee. Tasks let you define repeating workflows. "Every time I push code, run tests." "Every time I create a new file, add boilerplate." "Every time I start a session, check for errors." Automated. Hands-free. Consistent. You're doing these things manually every single day. The same checks. The same steps. The same routine. Tasks do them automatically. So you can focus on the work that actually makes money. Every manual task you automate is time you get back. And time is the only thing you can never make more of. Save this post. Follow Himanshu Kumar for the task automation templates that run my entire workflow. ↓ 14. Explore Features Most People Never Touch. The video covers features that 95% of Claude Code users don't know exist. Because they watched a 3-minute TikTok about Claude Code and think they're experts now. They're not. They're using 5% of a tool that can do everything. The full tutorial goes deep into features that most tutorials skip because they're "too advanced." They're not too advanced. They're too valuable for lazy creators to bother explaining. This video explains all of them. Clearly. For beginners. The 5% of features you don't know about are the 5% that make people rich. ↓ Let's zoom out. I just broke down 14 sections of Claude Code. Setup and installation. Desktop app. Dependencies. Code editor integration. Basic usage. Commands. Modes and shortcuts. Planning prompts. Model selection. Git and version control. Memory and Claude. MD. Tasks and automation. Advanced features. All in one video. All free. All beginner friendly. The person who masters even half of these in the next 2 weeks will be in the top 1% of Claude Code users. The top 1% of Claude Code users are the ones charging $5,000-$10,000 per project and building them in a single afternoon. Everyone else is asking ChatGPT to fix their resume. Same tools. Same access. Completely different outcomes. Because one person treats AI like a toy. And the other treats it like a business. ↓ Here's the hard truth nobody wants to hear. You don't have a talent problem. You don't have an intelligence problem. You don't have a resources problem. You have an action problem. Everything I just listed has a free tutorial right here in the attached video. 33 minutes. That's it. 33 minutes to learn the tool that people are using to build $5,000-$20,000/month businesses. You spent more time today scrolling Twitter than it takes to watch this video. You spent more time this week watching Netflix than it takes to master Claude Code basics. You spent more time this month doing nothing than it would take to completely change your income. The information is free. The tool is accessible. The opportunity is here. The only thing missing is you caring enough to start. ↓ CANCEL your plans this week. This isn't optional anymore. The people learning Claude Code right now will be building apps for the people who didn't learn it. That's not a prediction. That's already happening. Companies are replacing $150/hour developers with one person and Claude Code. If you code: learn Claude Code or become half as valuable by next year. If you don't code: learn Claude Code or miss the biggest opportunity to start earning from tech without a CS degree. There's no path forward that doesn't include AI coding tools. None. You have one window. Right now. This week. ↓ Here's your action plan for the next 7 days: Day 1: Watch the full video. Install Claude Code. Set up dependencies. Day 2: Learn basic usage. Try 5 different commands. Day 3: Write your first planning prompt. Build a small project. Day 4: Set up Claude. MD. Configure your memory file. Day 5: Master modes and shortcuts. Build a second project faster. Day 6: Set up Git integration. Automate with tasks. Day 7: Build something real. A tool, an app, a website. Ship it. 7 days. One tool. One completely different skill set. One completely different income potential. Or 7 more days of scrolling Twitter watching other people build things while you "plan to start." Your call. ↓ This is the most important video you'll watch this year. 33 minutes. Complete Claude Code mastery. From zero to building real projects. Save this post. Come back to it every single day this week. Check off each section as you complete it. Follow Himanshu Kumarfor daily Claude Code breakdowns, advanced tutorials, and the exact workflows that are turning beginners into $10K/month builders. The only thing between you and $10K/month with Claude Code is this video and 7 days. Don't waste them. You Must Follow me Himanshu Kumar, so i can send you DM.

Himanshu Kumar

85,668 views • 2 months ago

CANCEL Your Weekend Plans, and Learn Claude Code Today. $5,000/month. $10,000/month. $20,000/month. People are building entire apps and charging clients thousands using Claude Code. You're still Googling 'how to center a div.' While you're binge-watching a show you won't remember next week, a 19 year old with zero coding experience just built a $5,000 SaaS product in one afternoon using the tool I'm about to break down. Same laptop. Same internet. Same 24 hours. He has Claude Code. You have Netflix. That's the only difference. This YouTube video is a goldmine. Full Claude Code tutorial. Beginner to pro. Every feature. Every setup step. Every best practice. Zero prior knowledge needed. Save it. Watch it tonight. Not tomorrow. Tonight. Save this post. This is your complete Claude Code roadmap. Lose it and you lose the next 12 months of income. Follow Himanshu Kumar so you don't miss the breakdowns for each feature. ↓ 1. Understand What Claude Code Actually Is. You think Claude Code is just another chatbot. It's not. And that misunderstanding is why you're broke. ChatGPT gives you text. Claude Code gives you software. It runs in your terminal. It reads your entire codebase. It writes files directly to your project. It runs commands on your machine. It debugs errors autonomously. It builds features end to end. You're not chatting. You're deploying a developer. One that works 24/7. Never asks for a raise. Never calls in sick. Never pushes broken code at 5 PM on a Friday. People are charging clients $5,000-$10,000 for apps they built with Claude Code in 3 hours. And you didn't even know this tool existed because you're still asking ChatGPT to write you a to-do list. The gap between you and people making money with AI isn't intelligence. It's awareness. Now you're aware. Save this post. Follow Himanshu Kumar for the complete breakdown of every Claude Code feature. ↓ 2. Set Up Claude Code Properly. Most people quit here. "It's too complicated." "I don't know terminal." "I'll set it up later." Later never comes. And "complicated" means "I watched for 30 seconds and gave up." The setup takes 10 minutes. Install Node.js. Install Claude Code via npm. Authenticate your account. Open your terminal. Done. 10 minutes. You spent longer this morning deciding what to have for breakfast. The video walks through every single click. Every command. Every screen. Assuming you know absolutely nothing. If you can download an app on your phone, you can set up Claude Code. It's the same level of difficulty. But you'll still tell yourself it's "too technical" because that excuse is more comfortable than admitting you're just scared to try something new. This is the setup that everything else builds on. Skip it and nothing works. ↓ 3. Use the Desktop App. You don't even need to live in the terminal if you don't want to. Claude Code has a desktop app. Clean interface. Visual feedback. Everything you need without touching command line. But here's the thing most people don't know: The desktop app isn't just a pretty wrapper. It lets you manage projects visually. See file changes in real time. Switch between projects instantly. The people making money with Claude Code use the desktop app for client projects because it's faster to manage multiple builds simultaneously. You're still opening 14 browser tabs to organize one project. They open one app and everything's there. Efficiency isn't a personality trait. It's a tool choice. Save this post. Follow Himanshu Kumar for the desktop app workflow that handles 5 client projects at once. ↓ 4. Install the Right Dependencies. This is where beginners silently fail and blame the tool. Claude Code needs certain dependencies installed to work properly. Miss one and everything breaks. Then you go on Twitter and say "Claude Code doesn't work." It works fine. You just didn't read the setup guide. The video covers every dependency you need. What to install. How to install it. How to verify it's working. No guessing. No Stack Overflow rabbit holes at midnight. No "why isn't this working" for 3 hours. Watch the dependency section once. Follow every step. Never deal with setup issues again. You spent more time last week troubleshooting a printer than this takes. ↓ 5. Work Inside Your Code Editor. Claude Code integrates directly with your code editor. VS Code. Cursor. Whatever you use. It's not a separate window you alt-tab between. It's right there. In your workflow. You type a request. Claude writes the code. The code appears in your editor. You review it. Accept it. Done. No copy pasting between windows. No reformatting code that got mangled in transit. No "which version was the right one." It's like pair programming with someone who never gets distracted, never argues about naming conventions, and actually writes code that works on the first try. Your current coding process is: Google the problem, read 5 answers on Stack Overflow, copy the wrong one, debug for an hour, find the right one, paste it in, break something else, repeat. Claude Code's process is: describe what you want, get working code, move on with your life. Same hour. One method produces working software. The other produces frustration and a browser history full of Stack Overflow tabs. Stop coding the hard way. Save this post. Follow Himanshu Kumar for code editor setup guides and integration tips. ↓ 6. Master Basic Usage. Most people learn 5% of a tool and say they "know" it. You "know" Photoshop because you can crop an image. You "know" Excel because you can sum a column. You "know" Claude Code because you asked it one question. Basic usage means: How to give Claude Code context about your project. How to ask for changes to existing code. How to generate new files and features. How to review what Claude produces. How to iterate when the output isn't perfect. These basics are the foundation of everything. Skip them and every advanced feature feels confusing. Master them and every advanced feature feels obvious. The video breaks down each one with real examples. Not theory. Actual usage on actual projects. You've been using AI tools at 5% capacity and wondering why your results are 5% of what others get. Save this post. Follow Himanshu Kumar for daily Claude Code usage tips. ↓ 7. Learn Every Command. Claude Code has commands that most users never discover. Because most users type one message and expect magic. That's not how professionals use it. Professionals use specific commands that tell Claude Code exactly what to do, how to do it, and what constraints to follow. The difference between a beginner and someone making $10K/month with Claude Code is knowing which command to use and when. The video walks through every single one. Not just what they do. But when to use each one. And why one command is better than another for specific situations. You've been using Claude Code like a hammer. These commands turn it into a full toolbox. Stop treating a power tool like a blunt instrument. Save this post. Follow Himanshu Kumar for the command cheat sheet I use daily. ↓ 8. Understand Modes and Shortcuts. Speed matters. The person who builds an app in 2 hours charges $5,000. The person who builds the same app in 2 days charges $2,000. Same app. Same quality. Different speed. Different income. Claude Code has modes that change how it operates. And shortcuts that cut your workflow time in half. Most people don't know either exists. They use Claude Code in default mode for everything. Like driving a car in first gear on the highway. Technically it works. But everyone is passing you. The video shows you every mode. Every shortcut. Every time-saving trick that separates the people charging $2,000 per project from the people charging $10,000. Speed is money. Literally. Save this post. Follow Himanshu Kumar for the shortcuts that cut my build time by 60%. ↓ 9. Write a Proper Planning Prompt. This is the section that separates amateurs from professionals. And it's the section most people skip. A planning prompt tells Claude Code what you're building before you start building it. Architecture. File structure. Technologies. Features. Constraints. Edge cases. Without a planning prompt, Claude Code guesses. And guessing produces garbage. With a planning prompt, Claude Code executes a clear plan. And clear plans produce working software. The video shows you exactly how to write a planning prompt that makes Claude Code produce professional-grade output on the first try. "But I just want to start coding." That's why your code breaks every time. That's why you restart projects 4 times. That's why nothing you build ever gets finished. Because you refuse to plan. A 5-minute planning prompt saves you 5 hours of debugging. But you'd rather skip the 5 minutes and suffer through the 5 hours because patience isn't your thing. And that's exactly why you're not making money. Planning is the most underpaid skill in coding. And the most overpaid when you master it. Save this post. Follow Himanshu Kumar for the planning prompt templates I use for every client project. ↓ 10. Choose the Right Model. Claude Code lets you select different AI models. Not all models are the same. Not all tasks need the same model. Using the most powerful model for a simple task wastes credits. Using a basic model for a complex task wastes time. The video explains: Which model to use for quick fixes. Which model to use for complex architecture. Which model to use for debugging. Which model to use for code generation. Most people pick one model and use it for everything. That's like using a sledgehammer to hang a picture frame. Model selection is strategy. And strategy is money. The people making $10K/month with Claude Code are strategic about every credit they spend. You're burning through credits because you use the most expensive model to write a hello world. ↓ 11. Use Git and Version Control. If you're not using version control, you're one mistake away from losing everything. Claude Code integrates with Git. Every change tracked. Every version saved. Every mistake reversible. Without Git: Claude makes a change. It breaks something. You can't undo it. You start over. 3 hours wasted. With Git: Claude makes a change. It breaks something. You roll back in 5 seconds. Keep working. Version control isn't optional. It's insurance. And the people not using it are the same people who say "I lost my entire project" like it's something that just happens. It doesn't just happen. It happens because you didn't set up Git. The video walks through the entire Git integration. Save this post. Follow Himanshu Kumar for the Git workflow that's saved every project I've ever built. ↓ 12. Set Up Claude.MD and Memory. This is the feature that makes Claude Code feel like a real team member instead of a stranger you explain everything to every time. ClaudeMD is a memory file. You tell Claude Code about your project once. It remembers forever. Coding style preferences. Project architecture decisions. Technology stack. File naming conventions. Business logic rules. Without ClaudeMD: Every new conversation starts from zero. You explain the same things repeatedly. Output is inconsistent. With ClaudeMD: Claude knows your project. Claude follows your rules. Claude produces consistent, professional code. The difference between a sloppy freelancer and a reliable agency is consistency. Claude. MD gives you consistency without the agency overhead. Most people don't set this up and wonder why Claude Code gives different answers every time. ↓ 13. Automate with Tasks. This is where Claude Code stops being a tool and starts being an employee. Tasks let you define repeating workflows. "Every time I push code, run tests." "Every time I create a new file, add boilerplate." "Every time I start a session, check for errors." Automated. Hands-free. Consistent. You're doing these things manually every single day. The same checks. The same steps. The same routine. Tasks do them automatically. So you can focus on the work that actually makes money. Every manual task you automate is time you get back. And time is the only thing you can never make more of. Save this post. Follow Himanshu Kumar for the task automation templates that run my entire workflow. ↓ 14. Explore Features Most People Never Touch. The video covers features that 95% of Claude Code users don't know exist. Because they watched a 3-minute TikTok about Claude Code and think they're experts now. They're not. They're using 5% of a tool that can do everything. The full tutorial goes deep into features that most tutorials skip because they're "too advanced." They're not too advanced. They're too valuable for lazy creators to bother explaining. This video explains all of them. Clearly. For beginners. The 5% of features you don't know about are the 5% that make people rich. ↓ Let's zoom out. I just broke down 14 sections of Claude Code. Setup and installation. Desktop app. Dependencies. Code editor integration. Basic usage. Commands. Modes and shortcuts. Planning prompts. Model selection. Git and version control. Memory and Claude. MD. Tasks and automation. Advanced features. All in one video. All free. All beginner friendly. The person who masters even half of these in the next 2 weeks will be in the top 1% of Claude Code users. The top 1% of Claude Code users are the ones charging $5,000-$10,000 per project and building them in a single afternoon. Everyone else is asking ChatGPT to fix their resume. Same tools. Same access. Completely different outcomes. Because one person treats AI like a toy. And the other treats it like a business. ↓ Here's the hard truth nobody wants to hear. You don't have a talent problem. You don't have an intelligence problem. You don't have a resources problem. You have an action problem. Everything I just listed has a free tutorial right here in the attached video. 33 minutes. That's it. 33 minutes to learn the tool that people are using to build $5,000-$20,000/month businesses. You spent more time today scrolling Twitter than it takes to watch this video. You spent more time this week watching Netflix than it takes to master Claude Code basics. You spent more time this month doing nothing than it would take to completely change your income. The information is free. The tool is accessible. The opportunity is here. The only thing missing is you caring enough to start. ↓ CANCEL your plans this week. This isn't optional anymore. The people learning Claude Code right now will be building apps for the people who didn't learn it. That's not a prediction. That's already happening. Companies are replacing $150/hour developers with one person and Claude Code. If you code: learn Claude Code or become half as valuable by next year. If you don't code: learn Claude Code or miss the biggest opportunity to start earning from tech without a CS degree. There's no path forward that doesn't include AI coding tools. None. You have one window. Right now. This week. ↓ Here's your action plan for the next 7 days: Day 1: Watch the full video. Install Claude Code. Set up dependencies. Day 2: Learn basic usage. Try 5 different commands. Day 3: Write your first planning prompt. Build a small project. Day 4: Set up Claude. MD. Configure your memory file. Day 5: Master modes and shortcuts. Build a second project faster. Day 6: Set up Git integration. Automate with tasks. Day 7: Build something real. A tool, an app, a website. Ship it. 7 days. One tool. One completely different skill set. One completely different income potential. Or 7 more days of scrolling Twitter watching other people build things while you "plan to start." Your call. ↓ This is the most important video you'll watch this year. 33 minutes. Complete Claude Code mastery. From zero to building real projects. Save this post. Come back to it every single day this week. Check off each section as you complete it. Follow Himanshu Kumar for daily Claude Code breakdowns, advanced tutorials, and the exact workflows that are turning beginners into $10K/month builders. The only thing between you and $10K/month with Claude Code is this video and 7 days. Don't waste them. You Must Follow me Himanshu Kumar, so i can send you DM.
35:48

CANCEL Your Weekend Plans, and Learn Claude Code Today. $5,000/month. $10,000/month. $20,000/month. People are building entire apps and charging clients thousands using Claude Code. You're still Googling 'how to center a div.' While you're binge-watching a show you won't remember next week, a 19 year old with zero coding experience just built a $5,000 SaaS product in one afternoon using the tool I'm about to break down. Same laptop. Same internet. Same 24 hours. He has Claude Code. You have Netflix. That's the only difference. This YouTube video is a goldmine. Full Claude Code tutorial. Beginner to pro. Every feature. Every setup step. Every best practice. Zero prior knowledge needed. Save it. Watch it tonight. Not tomorrow. Tonight. Save this post. This is your complete Claude Code roadmap. Lose it and you lose the next 12 months of income. Follow Himanshu Kumar so you don't miss the breakdowns for each feature. ↓ 1. Understand What Claude Code Actually Is. You think Claude Code is just another chatbot. It's not. And that misunderstanding is why you're broke. ChatGPT gives you text. Claude Code gives you software. It runs in your terminal. It reads your entire codebase. It writes files directly to your project. It runs commands on your machine. It debugs errors autonomously. It builds features end to end. You're not chatting. You're deploying a developer. One that works 24/7. Never asks for a raise. Never calls in sick. Never pushes broken code at 5 PM on a Friday. People are charging clients $5,000-$10,000 for apps they built with Claude Code in 3 hours. And you didn't even know this tool existed because you're still asking ChatGPT to write you a to-do list. The gap between you and people making money with AI isn't intelligence. It's awareness. Now you're aware. Save this post. Follow Himanshu Kumar for the complete breakdown of every Claude Code feature. ↓ 2. Set Up Claude Code Properly. Most people quit here. "It's too complicated." "I don't know terminal." "I'll set it up later." Later never comes. And "complicated" means "I watched for 30 seconds and gave up." The setup takes 10 minutes. Install Node.js. Install Claude Code via npm. Authenticate your account. Open your terminal. Done. 10 minutes. You spent longer this morning deciding what to have for breakfast. The video walks through every single click. Every command. Every screen. Assuming you know absolutely nothing. If you can download an app on your phone, you can set up Claude Code. It's the same level of difficulty. But you'll still tell yourself it's "too technical" because that excuse is more comfortable than admitting you're just scared to try something new. This is the setup that everything else builds on. Skip it and nothing works. ↓ 3. Use the Desktop App. You don't even need to live in the terminal if you don't want to. Claude Code has a desktop app. Clean interface. Visual feedback. Everything you need without touching command line. But here's the thing most people don't know: The desktop app isn't just a pretty wrapper. It lets you manage projects visually. See file changes in real time. Switch between projects instantly. The people making money with Claude Code use the desktop app for client projects because it's faster to manage multiple builds simultaneously. You're still opening 14 browser tabs to organize one project. They open one app and everything's there. Efficiency isn't a personality trait. It's a tool choice. Save this post. Follow Himanshu Kumar for the desktop app workflow that handles 5 client projects at once. ↓ 4. Install the Right Dependencies. This is where beginners silently fail and blame the tool. Claude Code needs certain dependencies installed to work properly. Miss one and everything breaks. Then you go on Twitter and say "Claude Code doesn't work." It works fine. You just didn't read the setup guide. The video covers every dependency you need. What to install. How to install it. How to verify it's working. No guessing. No Stack Overflow rabbit holes at midnight. No "why isn't this working" for 3 hours. Watch the dependency section once. Follow every step. Never deal with setup issues again. You spent more time last week troubleshooting a printer than this takes. ↓ 5. Work Inside Your Code Editor. Claude Code integrates directly with your code editor. VS Code. Cursor. Whatever you use. It's not a separate window you alt-tab between. It's right there. In your workflow. You type a request. Claude writes the code. The code appears in your editor. You review it. Accept it. Done. No copy pasting between windows. No reformatting code that got mangled in transit. No "which version was the right one." It's like pair programming with someone who never gets distracted, never argues about naming conventions, and actually writes code that works on the first try. Your current coding process is: Google the problem, read 5 answers on Stack Overflow, copy the wrong one, debug for an hour, find the right one, paste it in, break something else, repeat. Claude Code's process is: describe what you want, get working code, move on with your life. Same hour. One method produces working software. The other produces frustration and a browser history full of Stack Overflow tabs. Stop coding the hard way. Save this post. Follow Himanshu Kumar for code editor setup guides and integration tips. ↓ 6. Master Basic Usage. Most people learn 5% of a tool and say they "know" it. You "know" Photoshop because you can crop an image. You "know" Excel because you can sum a column. You "know" Claude Code because you asked it one question. Basic usage means: How to give Claude Code context about your project. How to ask for changes to existing code. How to generate new files and features. How to review what Claude produces. How to iterate when the output isn't perfect. These basics are the foundation of everything. Skip them and every advanced feature feels confusing. Master them and every advanced feature feels obvious. The video breaks down each one with real examples. Not theory. Actual usage on actual projects. You've been using AI tools at 5% capacity and wondering why your results are 5% of what others get. Save this post. Follow Himanshu Kumar for daily Claude Code usage tips. ↓ 7. Learn Every Command. Claude Code has commands that most users never discover. Because most users type one message and expect magic. That's not how professionals use it. Professionals use specific commands that tell Claude Code exactly what to do, how to do it, and what constraints to follow. The difference between a beginner and someone making $10K/month with Claude Code is knowing which command to use and when. The video walks through every single one. Not just what they do. But when to use each one. And why one command is better than another for specific situations. You've been using Claude Code like a hammer. These commands turn it into a full toolbox. Stop treating a power tool like a blunt instrument. Save this post. Follow Himanshu Kumar for the command cheat sheet I use daily. ↓ 8. Understand Modes and Shortcuts. Speed matters. The person who builds an app in 2 hours charges $5,000. The person who builds the same app in 2 days charges $2,000. Same app. Same quality. Different speed. Different income. Claude Code has modes that change how it operates. And shortcuts that cut your workflow time in half. Most people don't know either exists. They use Claude Code in default mode for everything. Like driving a car in first gear on the highway. Technically it works. But everyone is passing you. The video shows you every mode. Every shortcut. Every time-saving trick that separates the people charging $2,000 per project from the people charging $10,000. Speed is money. Literally. Save this post. Follow Himanshu Kumar for the shortcuts that cut my build time by 60%. ↓ 9. Write a Proper Planning Prompt. This is the section that separates amateurs from professionals. And it's the section most people skip. A planning prompt tells Claude Code what you're building before you start building it. Architecture. File structure. Technologies. Features. Constraints. Edge cases. Without a planning prompt, Claude Code guesses. And guessing produces garbage. With a planning prompt, Claude Code executes a clear plan. And clear plans produce working software. The video shows you exactly how to write a planning prompt that makes Claude Code produce professional-grade output on the first try. "But I just want to start coding." That's why your code breaks every time. That's why you restart projects 4 times. That's why nothing you build ever gets finished. Because you refuse to plan. A 5-minute planning prompt saves you 5 hours of debugging. But you'd rather skip the 5 minutes and suffer through the 5 hours because patience isn't your thing. And that's exactly why you're not making money. Planning is the most underpaid skill in coding. And the most overpaid when you master it. Save this post. Follow Himanshu Kumar for the planning prompt templates I use for every client project. ↓ 10. Choose the Right Model. Claude Code lets you select different AI models. Not all models are the same. Not all tasks need the same model. Using the most powerful model for a simple task wastes credits. Using a basic model for a complex task wastes time. The video explains: Which model to use for quick fixes. Which model to use for complex architecture. Which model to use for debugging. Which model to use for code generation. Most people pick one model and use it for everything. That's like using a sledgehammer to hang a picture frame. Model selection is strategy. And strategy is money. The people making $10K/month with Claude Code are strategic about every credit they spend. You're burning through credits because you use the most expensive model to write a hello world. ↓ 11. Use Git and Version Control. If you're not using version control, you're one mistake away from losing everything. Claude Code integrates with Git. Every change tracked. Every version saved. Every mistake reversible. Without Git: Claude makes a change. It breaks something. You can't undo it. You start over. 3 hours wasted. With Git: Claude makes a change. It breaks something. You roll back in 5 seconds. Keep working. Version control isn't optional. It's insurance. And the people not using it are the same people who say "I lost my entire project" like it's something that just happens. It doesn't just happen. It happens because you didn't set up Git. The video walks through the entire Git integration. Save this post. Follow Himanshu Kumar for the Git workflow that's saved every project I've ever built. ↓ 12. Set Up Claude.MD and Memory. This is the feature that makes Claude Code feel like a real team member instead of a stranger you explain everything to every time. ClaudeMD is a memory file. You tell Claude Code about your project once. It remembers forever. Coding style preferences. Project architecture decisions. Technology stack. File naming conventions. Business logic rules. Without ClaudeMD: Every new conversation starts from zero. You explain the same things repeatedly. Output is inconsistent. With ClaudeMD: Claude knows your project. Claude follows your rules. Claude produces consistent, professional code. The difference between a sloppy freelancer and a reliable agency is consistency. Claude. MD gives you consistency without the agency overhead. Most people don't set this up and wonder why Claude Code gives different answers every time. ↓ 13. Automate with Tasks. This is where Claude Code stops being a tool and starts being an employee. Tasks let you define repeating workflows. "Every time I push code, run tests." "Every time I create a new file, add boilerplate." "Every time I start a session, check for errors." Automated. Hands-free. Consistent. You're doing these things manually every single day. The same checks. The same steps. The same routine. Tasks do them automatically. So you can focus on the work that actually makes money. Every manual task you automate is time you get back. And time is the only thing you can never make more of. Save this post. Follow Himanshu Kumar for the task automation templates that run my entire workflow. ↓ 14. Explore Features Most People Never Touch. The video covers features that 95% of Claude Code users don't know exist. Because they watched a 3-minute TikTok about Claude Code and think they're experts now. They're not. They're using 5% of a tool that can do everything. The full tutorial goes deep into features that most tutorials skip because they're "too advanced." They're not too advanced. They're too valuable for lazy creators to bother explaining. This video explains all of them. Clearly. For beginners. The 5% of features you don't know about are the 5% that make people rich. ↓ Let's zoom out. I just broke down 14 sections of Claude Code. Setup and installation. Desktop app. Dependencies. Code editor integration. Basic usage. Commands. Modes and shortcuts. Planning prompts. Model selection. Git and version control. Memory and Claude. MD. Tasks and automation. Advanced features. All in one video. All free. All beginner friendly. The person who masters even half of these in the next 2 weeks will be in the top 1% of Claude Code users. The top 1% of Claude Code users are the ones charging $5,000-$10,000 per project and building them in a single afternoon. Everyone else is asking ChatGPT to fix their resume. Same tools. Same access. Completely different outcomes. Because one person treats AI like a toy. And the other treats it like a business. ↓ Here's the hard truth nobody wants to hear. You don't have a talent problem. You don't have an intelligence problem. You don't have a resources problem. You have an action problem. Everything I just listed has a free tutorial right here in the attached video. 33 minutes. That's it. 33 minutes to learn the tool that people are using to build $5,000-$20,000/month businesses. You spent more time today scrolling Twitter than it takes to watch this video. You spent more time this week watching Netflix than it takes to master Claude Code basics. You spent more time this month doing nothing than it would take to completely change your income. The information is free. The tool is accessible. The opportunity is here. The only thing missing is you caring enough to start. ↓ CANCEL your plans this week. This isn't optional anymore. The people learning Claude Code right now will be building apps for the people who didn't learn it. That's not a prediction. That's already happening. Companies are replacing $150/hour developers with one person and Claude Code. If you code: learn Claude Code or become half as valuable by next year. If you don't code: learn Claude Code or miss the biggest opportunity to start earning from tech without a CS degree. There's no path forward that doesn't include AI coding tools. None. You have one window. Right now. This week. ↓ Here's your action plan for the next 7 days: Day 1: Watch the full video. Install Claude Code. Set up dependencies. Day 2: Learn basic usage. Try 5 different commands. Day 3: Write your first planning prompt. Build a small project. Day 4: Set up Claude. MD. Configure your memory file. Day 5: Master modes and shortcuts. Build a second project faster. Day 6: Set up Git integration. Automate with tasks. Day 7: Build something real. A tool, an app, a website. Ship it. 7 days. One tool. One completely different skill set. One completely different income potential. Or 7 more days of scrolling Twitter watching other people build things while you "plan to start." Your call. ↓ This is the most important video you'll watch this year. 33 minutes. Complete Claude Code mastery. From zero to building real projects. Save this post. Come back to it every single day this week. Check off each section as you complete it. Follow Himanshu Kumar for daily Claude Code breakdowns, advanced tutorials, and the exact workflows that are turning beginners into $10K/month builders. The only thing between you and $10K/month with Claude Code is this video and 7 days. Don't waste them. You Must Follow me Himanshu Kumar, so i can send you DM.

Himanshu Kumar

101,105 views • 3 months ago

something strange is happening... i don't think we've fully processed it yet. over the last few weeks, i've watched entire functions of a company collapse into software. desktop automation → heyclicky by Farza 🇵🇰🇺🇸 app dev → superapp ai Vitalik Kotik content → arcads by Romain Torres workflows → n8n + claude ops automation → polsia by Ben Cera memory layer → shram by Ojasvika Sahu (Oz) web dev → lovable by Anton Osika presentations → gamma by Grant Lee crawl and research → exa by Will Bryk i mean the list is endless. on a daily basis, i use granola, elevenlabs, heygen, canva, wisprflow, and so many others i know many of these tools are far from perfect, they break often, maybe the founders' claims are too tall but for me, its not about what exists today but what the world will look like very soon just last week, i randomly built an app with superapp, created ugc with arcads for distribution, setup an n8n (with cowork) took me total 15 mintues which is less than how long it took me to make this video and edit with canva (i have not tried ai video edit tools yet) it didn't even cross my mind that i need to hire someone... for anything. a few years ago that would've sounded ridiculous. today it's... normal. anything else is ridiculous. and that's the part that fascinates me. i don't think we're seeing the end state of this technology. i think we're seeing the worst version we'll ever use. the slowest. the least capable. the most expensive. which means the future is probably much stranger than we imagine. what happens when every person can build products? what happens when every business can create unlimited content? what happens when a team of one can operate like a team of fifty? honestly, i have no idea. and i don't think anyone else does either. but it feels a lot like standing at the beginning of something much bigger than most people realize. the tools are already impressive. what's really crazy is how early it still feels... which ai tools do you use on a daily basis? i want to play with more and absorb as much as i can (lmk in the comments - if its underdog, drop the tool link)
0:46

something strange is happening... i don't think we've fully processed it yet. over the last few weeks, i've watched entire functions of a company collapse into software. desktop automation → heyclicky by Farza 🇵🇰🇺🇸 app dev → superapp ai Vitalik Kotik content → arcads by Romain Torres workflows → n8n + claude ops automation → polsia by Ben Cera memory layer → shram by Ojasvika Sahu (Oz) web dev → lovable by Anton Osika presentations → gamma by Grant Lee crawl and research → exa by Will Bryk i mean the list is endless. on a daily basis, i use granola, elevenlabs, heygen, canva, wisprflow, and so many others i know many of these tools are far from perfect, they break often, maybe the founders' claims are too tall but for me, its not about what exists today but what the world will look like very soon just last week, i randomly built an app with superapp, created ugc with arcads for distribution, setup an n8n (with cowork) took me total 15 mintues which is less than how long it took me to make this video and edit with canva (i have not tried ai video edit tools yet) it didn't even cross my mind that i need to hire someone... for anything. a few years ago that would've sounded ridiculous. today it's... normal. anything else is ridiculous. and that's the part that fascinates me. i don't think we're seeing the end state of this technology. i think we're seeing the worst version we'll ever use. the slowest. the least capable. the most expensive. which means the future is probably much stranger than we imagine. what happens when every person can build products? what happens when every business can create unlimited content? what happens when a team of one can operate like a team of fifty? honestly, i have no idea. and i don't think anyone else does either. but it feels a lot like standing at the beginning of something much bigger than most people realize. the tools are already impressive. what's really crazy is how early it still feels... which ai tools do you use on a daily basis? i want to play with more and absorb as much as i can (lmk in the comments - if its underdog, drop the tool link)

Kritarth Mittal | Soshals

32,875 views • 1 month ago

Came across this information, so I copied it for you all to read. After reading it … watch the video attached and laugh your arse off. Because Obama set all this up … it’s one of those ‘unintended consequences’ which worked in Trumps favor. Trump is using it right, Democrats used it as a silent weapon. ———————————————— “I came across a lawyer, Tom Renz, who actually read Trump's DOGE Executive Order and, expecting some illegal power grab, found it to be airtight.” “Turns out Trump and Musk didn't create anything. Obama did. Obama created United States Digital Service (USDS) in 2014. It was meant as a bureaucratic patch job to fix the Obamacare website meltdown.” “Fast forward to 2025. Trump rebrands it DOGE (United States DOGE Service). Keeps the acronym, keeps the funding, but gives it a whole new mission: Find the Receipts Legally untouchable because it was already fully funded and operational.” “Trump invokes 5 USC 3161, which allows him to create temporary hiring authorities. DOGE teams get embedded inside every single federal agency. Each team consists of a lawyer, HR rep, a zoomer nerd, and an investigator. They report to DOGE, not the agency they're embedded in.” “But wait, there's more! Trump invokes 44 USC Chapter 35, which governs federal IT and cybersecurity oversight. Since USDS was originally an IT oversight body, DOGE now has full access to all federal data systems. Yes, that’s right. All of them.” “His executive order is written to block legal challenges. Includes language that overrides conflicting executive orders. Orders every agency to comply. Refusal means they violate presidential authority.” “Congress can't defund it because it's not a new program, just a repurposed one. DOJ can't sue for overreach because Trump used existing laws exactly as written. Democrats trying to file legal challenges run into standing issues because DOGE operates within existing frameworks. Obama literally built the perfect Administrative (read: Deep State) IT backdoor.” “Trump and Musk just hacked the system and took the admin controls. Musk now has legal oversight of every major agency's internal systems. The Administrative State can't stop it without rewriting multiple federal laws.” “They legally outplayed the system and there’s nothing anyone can do about it.” “Obama created DOGE.”
0:44

Came across this information, so I copied it for you all to read. After reading it … watch the video attached and laugh your arse off. Because Obama set all this up … it’s one of those ‘unintended consequences’ which worked in Trumps favor. Trump is using it right, Democrats used it as a silent weapon. ———————————————— “I came across a lawyer, Tom Renz, who actually read Trump's DOGE Executive Order and, expecting some illegal power grab, found it to be airtight.” “Turns out Trump and Musk didn't create anything. Obama did. Obama created United States Digital Service (USDS) in 2014. It was meant as a bureaucratic patch job to fix the Obamacare website meltdown.” “Fast forward to 2025. Trump rebrands it DOGE (United States DOGE Service). Keeps the acronym, keeps the funding, but gives it a whole new mission: Find the Receipts Legally untouchable because it was already fully funded and operational.” “Trump invokes 5 USC 3161, which allows him to create temporary hiring authorities. DOGE teams get embedded inside every single federal agency. Each team consists of a lawyer, HR rep, a zoomer nerd, and an investigator. They report to DOGE, not the agency they're embedded in.” “But wait, there's more! Trump invokes 44 USC Chapter 35, which governs federal IT and cybersecurity oversight. Since USDS was originally an IT oversight body, DOGE now has full access to all federal data systems. Yes, that’s right. All of them.” “His executive order is written to block legal challenges. Includes language that overrides conflicting executive orders. Orders every agency to comply. Refusal means they violate presidential authority.” “Congress can't defund it because it's not a new program, just a repurposed one. DOJ can't sue for overreach because Trump used existing laws exactly as written. Democrats trying to file legal challenges run into standing issues because DOGE operates within existing frameworks. Obama literally built the perfect Administrative (read: Deep State) IT backdoor.” “Trump and Musk just hacked the system and took the admin controls. Musk now has legal oversight of every major agency's internal systems. The Administrative State can't stop it without rewriting multiple federal laws.” “They legally outplayed the system and there’s nothing anyone can do about it.” “Obama created DOGE.”

C-Reason🇺🇸

99,993 views • 1 year ago

I've built a multiplayer survival game for the browser in 30 days and I didnt write a single line of code 🤯 So I'd like to write my notes about it once the deadline is done now. The last 20% of a project is indeed the hardest part of it all. In the last 2 days i've been working on the final version of Hollowlands for @levelsio's 2026 #vibejam I worked a lot! I fixed a lot of bugs, tested a lot playing with my wife. Fixed more bugs... But now, thank God, I have the final result! The game looks good, yes. I've spent half of the jam just tweaking every single detail of the procedural world generation. And It was worth it! The game still runs well on most devices and still has less than 20MB in size. Which is pretty impressive to me. The process of building was very straighforward: 1. I used Three.js + React to create the game. Before I started I created a huge document defining every rule i'd like the codebase to be implemented upon. It had clean code rules, archtecture decisions, ECS principles (good for games), and so on. This helped a lot constrain the AI to maintain the code maintainable and separated into clear domains (systems). This document was made partially by me given my previous experience building web games (I've made a lot of mistakes in the past and made sure they will not repeat again) and partially AI suggesting best practices. 2. For every feature I prompted the AI, I was very specific on details that I'd like implemented. If I knew what I was doing, I was more specific on the "how" I wanted to be done. If I didnt know what was doing I first asked the AI to brainstorm possibilities with me, based on industry standards, pros and cons, and so on. Then I would decide what path to go. 3. Every single feature I used Leva for tweaking the values. So for example, the size of the trees, colors, distance between objects, animation speed, etc. Everything I have a slider that I can adjust. 4. To make the game look good I used Tripo to create the models. To be honest it's not 100% perfect. If you check the character in game you can notice a few issues here and there (the arms lol), but I believe that it will keep getting better over time. 1 Year ago I tried and it wasnt even close to what it's now. Then I used a few post-processing + shaders + particles techniques to bring the "wow" factor. 5. I did only 1 feature at a time. And every change it was a commit with a clear message of what was done. This helped the AI fetch previous commit to understand what changed and know exactly what happened in the past. If I opened multiple terminals at once and blasted prompts the code and commit history would be a mess in a few days. And for every change the AI did, I asked it to do a Code Review of everything that was changed and look for violations on the document I wrote in the beggining defining the codebase guidelines. I realized that I pretty much applied software engineer principles using AI: Code, review and merge, code, review and merge... 6. On the last week I implemented the multiplayer using Colyseus ⚔️ which was pretty nice. I used AI to fetch the whole documentation and create a skill.md file that helped a lot. The creator of the framework Endel also did a extensive research on how real multiplayer games are implemented. It's open source and it was a gold mine for the AI to come up with the implementation for my game. You can ask him the link :) And that was it I think. I'm extremely tired now. The last 2 days was insane. The game's final version is not what I had in mind in the beginning of the jam. I had to cut a lot of cool features. But given the 30 days deadline I think it was a huge success. Hands down my best game ever made. Now I'll take a few days to rest and come back with more updates on the game. Maybe it can become a big deal in the future with more updates. Who knows. And in the event I win first place in this game jam, I'll use the money to fund my own game studio + cover the expenses of my child that is going to be born in September :) Cheers guys! If you have any question, feel free to reach out. I'll answer every non-bot comment in here haha Note: The link to play is in my profile
1:06

I've built a multiplayer survival game for the browser in 30 days and I didnt write a single line of code 🤯 So I'd like to write my notes about it once the deadline is done now. The last 20% of a project is indeed the hardest part of it all. In the last 2 days i've been working on the final version of Hollowlands for @levelsio's 2026 #vibejam I worked a lot! I fixed a lot of bugs, tested a lot playing with my wife. Fixed more bugs... But now, thank God, I have the final result! The game looks good, yes. I've spent half of the jam just tweaking every single detail of the procedural world generation. And It was worth it! The game still runs well on most devices and still has less than 20MB in size. Which is pretty impressive to me. The process of building was very straighforward: 1. I used Three.js + React to create the game. Before I started I created a huge document defining every rule i'd like the codebase to be implemented upon. It had clean code rules, archtecture decisions, ECS principles (good for games), and so on. This helped a lot constrain the AI to maintain the code maintainable and separated into clear domains (systems). This document was made partially by me given my previous experience building web games (I've made a lot of mistakes in the past and made sure they will not repeat again) and partially AI suggesting best practices. 2. For every feature I prompted the AI, I was very specific on details that I'd like implemented. If I knew what I was doing, I was more specific on the "how" I wanted to be done. If I didnt know what was doing I first asked the AI to brainstorm possibilities with me, based on industry standards, pros and cons, and so on. Then I would decide what path to go. 3. Every single feature I used Leva for tweaking the values. So for example, the size of the trees, colors, distance between objects, animation speed, etc. Everything I have a slider that I can adjust. 4. To make the game look good I used Tripo to create the models. To be honest it's not 100% perfect. If you check the character in game you can notice a few issues here and there (the arms lol), but I believe that it will keep getting better over time. 1 Year ago I tried and it wasnt even close to what it's now. Then I used a few post-processing + shaders + particles techniques to bring the "wow" factor. 5. I did only 1 feature at a time. And every change it was a commit with a clear message of what was done. This helped the AI fetch previous commit to understand what changed and know exactly what happened in the past. If I opened multiple terminals at once and blasted prompts the code and commit history would be a mess in a few days. And for every change the AI did, I asked it to do a Code Review of everything that was changed and look for violations on the document I wrote in the beggining defining the codebase guidelines. I realized that I pretty much applied software engineer principles using AI: Code, review and merge, code, review and merge... 6. On the last week I implemented the multiplayer using Colyseus ⚔️ which was pretty nice. I used AI to fetch the whole documentation and create a skill.md file that helped a lot. The creator of the framework Endel also did a extensive research on how real multiplayer games are implemented. It's open source and it was a gold mine for the AI to come up with the implementation for my game. You can ask him the link :) And that was it I think. I'm extremely tired now. The last 2 days was insane. The game's final version is not what I had in mind in the beginning of the jam. I had to cut a lot of cool features. But given the 30 days deadline I think it was a huge success. Hands down my best game ever made. Now I'll take a few days to rest and come back with more updates on the game. Maybe it can become a big deal in the future with more updates. Who knows. And in the event I win first place in this game jam, I'll use the money to fund my own game studio + cover the expenses of my child that is going to be born in September :) Cheers guys! If you have any question, feel free to reach out. I'll answer every non-bot comment in here haha Note: The link to play is in my profile

André → andreelias.dev

17,950 views • 2 months ago

Min Hee-jin (NewJeans Producer) NHK Music Interview 🔗 “Meticulously planned debut ‘Attention’” 🧢: When I was preparing to launch NewJeans, I really struggled with deciding what our first piece of content should be. I thought about it for a long time and considered many possibilities. It was a project that came with high expectations, and for me personally, it was also my first opportunity to prove myself. So how I presented it mattered enormously. Even down to the smallest details… like the impression the very first released photo might give, or what kind of impact we could make at launch. I thought hard about what kind of content would be the most effective… should it be a video or a photo? What time of day would be most effective to release it? I consider things like that very carefully. For example, the way a person experiences content at night versus during the day can feel quite different emotionally. So I even thought about those subtle aspects. Eventually, the conclusion I reached was: “Let’s make the most of our situation.” At the time, the members hadn’t been revealed, and no one knew how many of them there were or what kind of group this would be. So I wanted to maximize that curiosity. You know how the more something is concealed, the more curious people become? I wanted to build that curiosity to a peak and then release everything all at once. That’s why we decided not to release a teaser and instead go straight into a full music video. (This was actually inspired by Hyein suggesting we skip teasers.) I didn’t think still images or photos would be enough to fully convey the feeling I wanted to express. I felt that video and music together would evoke the emotional response I was looking for because people experience things synesthetically. When sound, image, and feeling come together, the emotional impact is stronger. I believed the best way to present the members’ images was through music and a moving picture… that’s why we led with a music video. In the debut music video, “Attention,” there’s a scene where the members act out a little drama. I paid very close attention to that moment and created music that would fit it precisely. For me, I don’t just make content… I design the entire process of how it should be shown for the greatest effect. And I believe that’s incredibly important. That first feeling someone gets when they encounter something… that emotion, that spark… is so important to me. I’m very detail-oriented, but I also value fun deeply. So rather than just releasing content, I want to enjoy the process leading up to it. Even when we released our second album, since we shot the entire music video across the country, the sequence of how we released the videos was critical for me. It’s hard to explain all this simply in an interview, but maybe some people noticed: the first content we released that time was actually a teaser for the last track, “ASAP,” and then we followed that with the full music video for “New Jeans,” which was the first track. That order was a carefully calculated strategy. It was designed to guide the audience’s emotional journey. Seeing the audience react just as I had hoped—that whole process was honestly so fun and thrilling for me. I think I really enjoy that kind of thing. ——— “How 'Ditto' was born” 🧢: People often praise the music of NewJeans, and I hear a lot of talk about genres. But actually, I don’t feel bound by genre at all. I love a wide variety of music. I’m not the type to insist on only one particular genre. What I love are songs that blend genres cleverly… those are my personal favorites. So going forward, my focus is not on genre but on whether something feels fresh and whether it can create an emotional moment. I don’t want to define what kind of music we make. And I think you have to experience the flow of the times to really understand what’s meaningful in a given moment. For instance, the song “Ditto” was chosen because it delivered emotion. It matched perfectly with the winter album concept I had envisioned, both in terms of timing and mood. When I hear a song, I tend to trust my gut. I have a pretty strong intuition for which songs will resonate. It’s not about objectively predicting what will be a “hit,” but about whether a song moves your heart… you can just feel it. Of course, my own taste plays a big role. But I think that’s actually my strength as a producer, not as a composer. When I hear a song, I can immediately picture the visual… what kind of story, what kind of vibe it could carry. That allows me to work faster. For example, when expressing something like school uniforms, there are so many possible variations. But I always like to start from the basics… what’s the original idea of a school uniform? I try to return to that. So with “Ditto,” I wanted to tap into something primal… the pure, basic feeling of liking someone. That kind of emotion is universal. Everyone has it; it’s wired into us. When I saw Director Shin Woo-seok’s interpretation of it, I thought, “Yes, that’s it.” That’s the kind of complete interpretation I look for. I believe the completion of a project comes from every person involved thinking about their part down to the final detail… the maximum quality they can bring out. My role is to unify and refine all of that. I draw out the essence of each person’s creativity, trimming away anything unnecessary. So the final product is something that’s polished and high-quality, just the way I envisioned it. That’s my working style. So it’s not like I’m fixated on retro or stuck in a particular style. I don’t think human taste has changed all that much. Things people liked in the past are the same things we like now. It’s just the form of expression that changes with time. I don’t feel bound by “past” or “present.” I don’t even think in those boundaries. To me, it’s all just good taste. You know how kids sometimes have their own little treasure boxes when they’re young? I think my work is kind of like that. I want to make things that never feel dated—that are timelessly enjoyable. ——— “Dance Expression and 'Hype Boy'” 🧢: I had a vision of what kind of girl group I wanted to create. That’s why I chose a song like “Hype Boy.” And to bring out that feeling, we created four different versions of the music video. Every choice had a purpose, everything was designed to maximize the experience of the song. “Hype Boy” is such a unique song. It has this strange, piercing melody that gives people chills in a good way. To emphasize that tingling feeling, I had to break away from the standard K-pop choreography format… you know, the kind where everyone is in perfect formation, doing synchronized moves. But our songs don’t suit that kind of choreography. Our dances are much harder. They require the body to move very naturally with the groove of the melody and beat. So I think our members are incredible. It’s not easy to express naturalness with your body, and you have to really enjoy it to make it look effortless. But they pulled it off so well. They’re still young, but they’re so talented. And through it all, I wanted to avoid making them look like they were performing just for business. I wanted them to show the pure joy and bright spirit that’s natural for people their age… genuine, carefree, radiant. ——— “The difference between NewJeans and conventional K-POP” 🧢: Ah, for me, it’s all about naturalness. And honestly, naturalness isn’t something you can produce or direct into existence. It comes from how I interact with the NewJeans members on a daily basis… what kind of environment they practice in, how they live and work. There are so many things that don’t appear on camera, but those unseen aspects have to be in place in order for true naturalness to come through. That’s why I wanted to create that kind of environment for the girls. And also, I wanted to shape my own working environment in that way too. Only then can something truly natural, something unforced and not overly stimulating, really come out. To begin with, I don’t believe anyone can be completely natural in front of a camera or under the gaze of others. It’s human nature to become self-conscious. That’s why I think naturalness is our strength, but it can’t be our concept. If you try to turn “naturalness” into a concept, it actually becomes incredibly artificial. So why do I place so much importance on naturalness? It’s because the girls are still so young. While other kids their age are going through school and having a wide range of life experiences, these members are living very different lives. Before they officially debuted, I told them, “This is like studying together with me.” Our standard contract is seven years, which is about the same length as going through high school and college in Korea: three years of high school and four years of university. So I told them, “We’re going to school together. We’re learning together.” And in that sense, I want to be a good teacher to them. They’re also surrounded by an incredibly professional team, people they’d never meet even in a traditional school setting. I’ve never really liked the word idol. These days, that word is used more like a job title, something manufactured by the industry, and it’s far from its original meaning. To me, the term idol feels misplaced. It doesn’t really reflect who these artists are or what they represent. And I’m not the kind of person who clings to labels or terminology. In fact, what I really want is to break the stereotypes and preconceptions that come with the idol industry. I want us to show people something different… to challenge those assumptions and redefine what this can look like. That’s the kind of mindset I have. ——— “Isn't it difficult for the members to express "naturalness"?” 🧢: There were a lot of things I considered when forming the group. First and foremost, I think it was important that the members shared a similar vibe… like how I prefer working with staff who align with my taste. It’s important for the crew to be on the same wavelength. And by that, I mean more than just getting along… it also extends to shared values. Of course, people won’t all share identical values, but when we’re facing in a similar direction, everything becomes easier. It’s also just more efficient to work with people who have overlapping tastes. Now, when it comes to our members, they each have their own individual tastes, but those preferences are still in development. Just like we all went through as kids, they’re still growing, still discovering themselves. They’re not in a finished state. So we didn’t cast them based on some complete or polished version of themselves. It wasn’t like, “This person is fully formed, let’s pick her.” It was more like, “Ah, she has potential, there’s something there.” That sense of a spark… those were the kinds of subtleties I paid attention to. I didn’t cast anyone just because they were pretty or could sing well. I don’t work like that. I really value those finer, more delicate aspects. Even the design of the light stick wasn’t something that came from a long strategic planning session… it was actually a spontaneous idea. I didn’t sit down and think, “Let’s make a light stick like this.” NewJeans didn’t have a fixed logo, but I felt we still needed a unifying symbol. So one night, just before going to sleep, I kept thinking about it. Right before dozing off, I started sketching and it turned into a rabbit’s face. When I drew it out, the shape just continued and turned into a bunny. To me, the NewJeans members are like little bunnies… playful, innocent. Their visuals also resemble rabbits in a way. And rabbits symbolize abundance. That made me think: “Ah, maybe our fans will multiply like rabbits. That would be great.” So that bunny face became both a symbol for the members and the fans. The image came to me all at once, and I imagined a venue completely filled with bunny light sticks. That vision led to the creation of the light stick itself. Since I always prioritize fun in everything I do, the next idea that came to mind was making the light stick customizable. I thought, “Wouldn’t it be great if fans could personalize their bunny?” That way, each rabbit would represent a different person’s character. So we included accessories, allowing everyone to customize their own bunny. It’s symbolic of all these different bunnies coming together and enjoying a good time as one. Our light stick has a big head, so when it’s used in a concert hall, it lights up in heart shapes that are very visible. That was the image I really wanted. And that bunny face… it’s also a heart. It represents both the face of NewJeans and our hearts. It’s the love we’re showing to our fans, and the love we want to receive in return. Every time I see it, I feel deeply moved. It’s very emotional for me because it’s a perfect realization of what I envisioned. As someone with a background in creative direction, there’s nothing more satisfying than seeing an idea materialize exactly the way you imagined it. That kind of work holds deep meaning for me. ⸻ 🧢: Looking back, I think in 2023 we were able to achieve almost everything we had hoped for. I’m so incredibly grateful for that. Of course, this is an ongoing challenge… and the better things go, the more pressure there is. That’s why I always try to return to my original mindset. Just like I tell the members, I try to remind myself of the beginning and keep things fun. Back then, when we were first putting out content, planning the music, and working on visuals, I felt this thrill… this rush of excitement. I don’t want to forget that feeling. So I try hard to engrave that emotion into every album we release. I’m constantly working to rediscover the joy in all of it. So for 2024, I hope everyone can look forward to us with fresh anticipation. And even if we come out with something completely new, I hope people will receive it warmly and with excitement. That’s really my deepest wish. 🙏
21:30

Min Hee-jin (NewJeans Producer) NHK Music Interview 🔗 “Meticulously planned debut ‘Attention’” 🧢: When I was preparing to launch NewJeans, I really struggled with deciding what our first piece of content should be. I thought about it for a long time and considered many possibilities. It was a project that came with high expectations, and for me personally, it was also my first opportunity to prove myself. So how I presented it mattered enormously. Even down to the smallest details… like the impression the very first released photo might give, or what kind of impact we could make at launch. I thought hard about what kind of content would be the most effective… should it be a video or a photo? What time of day would be most effective to release it? I consider things like that very carefully. For example, the way a person experiences content at night versus during the day can feel quite different emotionally. So I even thought about those subtle aspects. Eventually, the conclusion I reached was: “Let’s make the most of our situation.” At the time, the members hadn’t been revealed, and no one knew how many of them there were or what kind of group this would be. So I wanted to maximize that curiosity. You know how the more something is concealed, the more curious people become? I wanted to build that curiosity to a peak and then release everything all at once. That’s why we decided not to release a teaser and instead go straight into a full music video. (This was actually inspired by Hyein suggesting we skip teasers.) I didn’t think still images or photos would be enough to fully convey the feeling I wanted to express. I felt that video and music together would evoke the emotional response I was looking for because people experience things synesthetically. When sound, image, and feeling come together, the emotional impact is stronger. I believed the best way to present the members’ images was through music and a moving picture… that’s why we led with a music video. In the debut music video, “Attention,” there’s a scene where the members act out a little drama. I paid very close attention to that moment and created music that would fit it precisely. For me, I don’t just make content… I design the entire process of how it should be shown for the greatest effect. And I believe that’s incredibly important. That first feeling someone gets when they encounter something… that emotion, that spark… is so important to me. I’m very detail-oriented, but I also value fun deeply. So rather than just releasing content, I want to enjoy the process leading up to it. Even when we released our second album, since we shot the entire music video across the country, the sequence of how we released the videos was critical for me. It’s hard to explain all this simply in an interview, but maybe some people noticed: the first content we released that time was actually a teaser for the last track, “ASAP,” and then we followed that with the full music video for “New Jeans,” which was the first track. That order was a carefully calculated strategy. It was designed to guide the audience’s emotional journey. Seeing the audience react just as I had hoped—that whole process was honestly so fun and thrilling for me. I think I really enjoy that kind of thing. ——— “How 'Ditto' was born” 🧢: People often praise the music of NewJeans, and I hear a lot of talk about genres. But actually, I don’t feel bound by genre at all. I love a wide variety of music. I’m not the type to insist on only one particular genre. What I love are songs that blend genres cleverly… those are my personal favorites. So going forward, my focus is not on genre but on whether something feels fresh and whether it can create an emotional moment. I don’t want to define what kind of music we make. And I think you have to experience the flow of the times to really understand what’s meaningful in a given moment. For instance, the song “Ditto” was chosen because it delivered emotion. It matched perfectly with the winter album concept I had envisioned, both in terms of timing and mood. When I hear a song, I tend to trust my gut. I have a pretty strong intuition for which songs will resonate. It’s not about objectively predicting what will be a “hit,” but about whether a song moves your heart… you can just feel it. Of course, my own taste plays a big role. But I think that’s actually my strength as a producer, not as a composer. When I hear a song, I can immediately picture the visual… what kind of story, what kind of vibe it could carry. That allows me to work faster. For example, when expressing something like school uniforms, there are so many possible variations. But I always like to start from the basics… what’s the original idea of a school uniform? I try to return to that. So with “Ditto,” I wanted to tap into something primal… the pure, basic feeling of liking someone. That kind of emotion is universal. Everyone has it; it’s wired into us. When I saw Director Shin Woo-seok’s interpretation of it, I thought, “Yes, that’s it.” That’s the kind of complete interpretation I look for. I believe the completion of a project comes from every person involved thinking about their part down to the final detail… the maximum quality they can bring out. My role is to unify and refine all of that. I draw out the essence of each person’s creativity, trimming away anything unnecessary. So the final product is something that’s polished and high-quality, just the way I envisioned it. That’s my working style. So it’s not like I’m fixated on retro or stuck in a particular style. I don’t think human taste has changed all that much. Things people liked in the past are the same things we like now. It’s just the form of expression that changes with time. I don’t feel bound by “past” or “present.” I don’t even think in those boundaries. To me, it’s all just good taste. You know how kids sometimes have their own little treasure boxes when they’re young? I think my work is kind of like that. I want to make things that never feel dated—that are timelessly enjoyable. ——— “Dance Expression and 'Hype Boy'” 🧢: I had a vision of what kind of girl group I wanted to create. That’s why I chose a song like “Hype Boy.” And to bring out that feeling, we created four different versions of the music video. Every choice had a purpose, everything was designed to maximize the experience of the song. “Hype Boy” is such a unique song. It has this strange, piercing melody that gives people chills in a good way. To emphasize that tingling feeling, I had to break away from the standard K-pop choreography format… you know, the kind where everyone is in perfect formation, doing synchronized moves. But our songs don’t suit that kind of choreography. Our dances are much harder. They require the body to move very naturally with the groove of the melody and beat. So I think our members are incredible. It’s not easy to express naturalness with your body, and you have to really enjoy it to make it look effortless. But they pulled it off so well. They’re still young, but they’re so talented. And through it all, I wanted to avoid making them look like they were performing just for business. I wanted them to show the pure joy and bright spirit that’s natural for people their age… genuine, carefree, radiant. ——— “The difference between NewJeans and conventional K-POP” 🧢: Ah, for me, it’s all about naturalness. And honestly, naturalness isn’t something you can produce or direct into existence. It comes from how I interact with the NewJeans members on a daily basis… what kind of environment they practice in, how they live and work. There are so many things that don’t appear on camera, but those unseen aspects have to be in place in order for true naturalness to come through. That’s why I wanted to create that kind of environment for the girls. And also, I wanted to shape my own working environment in that way too. Only then can something truly natural, something unforced and not overly stimulating, really come out. To begin with, I don’t believe anyone can be completely natural in front of a camera or under the gaze of others. It’s human nature to become self-conscious. That’s why I think naturalness is our strength, but it can’t be our concept. If you try to turn “naturalness” into a concept, it actually becomes incredibly artificial. So why do I place so much importance on naturalness? It’s because the girls are still so young. While other kids their age are going through school and having a wide range of life experiences, these members are living very different lives. Before they officially debuted, I told them, “This is like studying together with me.” Our standard contract is seven years, which is about the same length as going through high school and college in Korea: three years of high school and four years of university. So I told them, “We’re going to school together. We’re learning together.” And in that sense, I want to be a good teacher to them. They’re also surrounded by an incredibly professional team, people they’d never meet even in a traditional school setting. I’ve never really liked the word idol. These days, that word is used more like a job title, something manufactured by the industry, and it’s far from its original meaning. To me, the term idol feels misplaced. It doesn’t really reflect who these artists are or what they represent. And I’m not the kind of person who clings to labels or terminology. In fact, what I really want is to break the stereotypes and preconceptions that come with the idol industry. I want us to show people something different… to challenge those assumptions and redefine what this can look like. That’s the kind of mindset I have. ——— “Isn't it difficult for the members to express "naturalness"?” 🧢: There were a lot of things I considered when forming the group. First and foremost, I think it was important that the members shared a similar vibe… like how I prefer working with staff who align with my taste. It’s important for the crew to be on the same wavelength. And by that, I mean more than just getting along… it also extends to shared values. Of course, people won’t all share identical values, but when we’re facing in a similar direction, everything becomes easier. It’s also just more efficient to work with people who have overlapping tastes. Now, when it comes to our members, they each have their own individual tastes, but those preferences are still in development. Just like we all went through as kids, they’re still growing, still discovering themselves. They’re not in a finished state. So we didn’t cast them based on some complete or polished version of themselves. It wasn’t like, “This person is fully formed, let’s pick her.” It was more like, “Ah, she has potential, there’s something there.” That sense of a spark… those were the kinds of subtleties I paid attention to. I didn’t cast anyone just because they were pretty or could sing well. I don’t work like that. I really value those finer, more delicate aspects. Even the design of the light stick wasn’t something that came from a long strategic planning session… it was actually a spontaneous idea. I didn’t sit down and think, “Let’s make a light stick like this.” NewJeans didn’t have a fixed logo, but I felt we still needed a unifying symbol. So one night, just before going to sleep, I kept thinking about it. Right before dozing off, I started sketching and it turned into a rabbit’s face. When I drew it out, the shape just continued and turned into a bunny. To me, the NewJeans members are like little bunnies… playful, innocent. Their visuals also resemble rabbits in a way. And rabbits symbolize abundance. That made me think: “Ah, maybe our fans will multiply like rabbits. That would be great.” So that bunny face became both a symbol for the members and the fans. The image came to me all at once, and I imagined a venue completely filled with bunny light sticks. That vision led to the creation of the light stick itself. Since I always prioritize fun in everything I do, the next idea that came to mind was making the light stick customizable. I thought, “Wouldn’t it be great if fans could personalize their bunny?” That way, each rabbit would represent a different person’s character. So we included accessories, allowing everyone to customize their own bunny. It’s symbolic of all these different bunnies coming together and enjoying a good time as one. Our light stick has a big head, so when it’s used in a concert hall, it lights up in heart shapes that are very visible. That was the image I really wanted. And that bunny face… it’s also a heart. It represents both the face of NewJeans and our hearts. It’s the love we’re showing to our fans, and the love we want to receive in return. Every time I see it, I feel deeply moved. It’s very emotional for me because it’s a perfect realization of what I envisioned. As someone with a background in creative direction, there’s nothing more satisfying than seeing an idea materialize exactly the way you imagined it. That kind of work holds deep meaning for me. ⸻ 🧢: Looking back, I think in 2023 we were able to achieve almost everything we had hoped for. I’m so incredibly grateful for that. Of course, this is an ongoing challenge… and the better things go, the more pressure there is. That’s why I always try to return to my original mindset. Just like I tell the members, I try to remind myself of the beginning and keep things fun. Back then, when we were first putting out content, planning the music, and working on visuals, I felt this thrill… this rush of excitement. I don’t want to forget that feeling. So I try hard to engrave that emotion into every album we release. I’m constantly working to rediscover the joy in all of it. So for 2024, I hope everyone can look forward to us with fresh anticipation. And even if we come out with something completely new, I hope people will receive it warmly and with excitement. That’s really my deepest wish. 🙏

1tokki

17,635 views • 11 months ago

Important announcement!!!🫵💥💫 Would you have a tooth pulled if it helped your chances to get an important grant funded? Absurd question (obviously), but the situation right now is so bad funding-wise, that I bet some of you actually considered it for a second… Well, don’t get desperate - we created a new tool that might help! (keep your teeth!) I’m excited to announce that as of today we are officially releasing “QED for Grants” for everyone. What started off as an extension of our existing paper review platform, grew in the last few months to an entirely new design. We’ve been working like crazy on this, and although we have more things we want to add in the (very near) future, we decided to release our AI for grants NOW, earlier than planned. It’s not perfect, no AI is, but for the first time, when I run my own grants through QED Science, I feel it gets the research, finds real problems, and gives me very useful feedback that I can implement before submission. It’s like sending it to 20 scientists from my domain, knowing they’ll agree to dedicate their entire week to carefully read and comment on every line. It’s very important to write your own grants yourself, it makes you think hard and you learn a lot from doing it, and q.e.d’s system is designed to preserve these positive aspects and augment them - you get feedback on your own writing, we don’t write for you!! But at the same time, a typical PI spends many months every year writing proposals and sadly only a tiny fraction gets funded, even if the ideas are good. When you are forced to submit an unreasonable amount of grants the quality of the writing drops, and rejection rates increase. Not because the essence is bad. It’s simply too competitive right now (the cuts made it so much worse) and if your proposal is not super clear and tight, and if it’s not a perfect fit for the grant you’re submitting, you’re doomed. Our grant solution is not an authoring, text-generating tool. It gives you constructive feedback on your writing (it comments on the deep things, not grammar and typos). It’s meant to help you with the questions that torment you late at night (“is this a good fit?”, “Is this novel enough?”, “Did I miss something?”). Tens of thousands of you already use q.e.d to improve your manuscripts and critically read papers, we built the grant tool by the same principles (you’ll identify many of the features that you told us you like). We’ve processed thousands of proposals, learned where things fail, where reviewers get stuck, why good ideas come out weak. We interviewed hundreds of scientists, and also experts who work in funding agencies and university research authorities, and implemented their feedback (we’re constantly looking for more feedback). Our AI is always happy to give you constructive (and polite!) critique, and it will go through your grant line-by-line, forcing you to improve clarity, flag weak points, and push the whole thing to a higher standard. We study, in scale, what gets funded and what doesn’t, and what is the perfect fit for each type of grant. So please, use it, pressure-test it, tell us where it fails, and together we’ll improve it every day to put you in the best position for actually testing your ideas in the real world. As always with q.e.d, the system is completely secured and private, and we are NOT training on your data (see the FAQ on our website). Please like, retweet, and share with your favorite colleagues! (link to the platform below in the thread👇)
0:53

Important announcement!!!🫵💥💫 Would you have a tooth pulled if it helped your chances to get an important grant funded? Absurd question (obviously), but the situation right now is so bad funding-wise, that I bet some of you actually considered it for a second… Well, don’t get desperate - we created a new tool that might help! (keep your teeth!) I’m excited to announce that as of today we are officially releasing “QED for Grants” for everyone. What started off as an extension of our existing paper review platform, grew in the last few months to an entirely new design. We’ve been working like crazy on this, and although we have more things we want to add in the (very near) future, we decided to release our AI for grants NOW, earlier than planned. It’s not perfect, no AI is, but for the first time, when I run my own grants through QED Science, I feel it gets the research, finds real problems, and gives me very useful feedback that I can implement before submission. It’s like sending it to 20 scientists from my domain, knowing they’ll agree to dedicate their entire week to carefully read and comment on every line. It’s very important to write your own grants yourself, it makes you think hard and you learn a lot from doing it, and q.e.d’s system is designed to preserve these positive aspects and augment them - you get feedback on your own writing, we don’t write for you!! But at the same time, a typical PI spends many months every year writing proposals and sadly only a tiny fraction gets funded, even if the ideas are good. When you are forced to submit an unreasonable amount of grants the quality of the writing drops, and rejection rates increase. Not because the essence is bad. It’s simply too competitive right now (the cuts made it so much worse) and if your proposal is not super clear and tight, and if it’s not a perfect fit for the grant you’re submitting, you’re doomed. Our grant solution is not an authoring, text-generating tool. It gives you constructive feedback on your writing (it comments on the deep things, not grammar and typos). It’s meant to help you with the questions that torment you late at night (“is this a good fit?”, “Is this novel enough?”, “Did I miss something?”). Tens of thousands of you already use q.e.d to improve your manuscripts and critically read papers, we built the grant tool by the same principles (you’ll identify many of the features that you told us you like). We’ve processed thousands of proposals, learned where things fail, where reviewers get stuck, why good ideas come out weak. We interviewed hundreds of scientists, and also experts who work in funding agencies and university research authorities, and implemented their feedback (we’re constantly looking for more feedback). Our AI is always happy to give you constructive (and polite!) critique, and it will go through your grant line-by-line, forcing you to improve clarity, flag weak points, and push the whole thing to a higher standard. We study, in scale, what gets funded and what doesn’t, and what is the perfect fit for each type of grant. So please, use it, pressure-test it, tell us where it fails, and together we’ll improve it every day to put you in the best position for actually testing your ideas in the real world. As always with q.e.d, the system is completely secured and private, and we are NOT training on your data (see the FAQ on our website). Please like, retweet, and share with your favorite colleagues! (link to the platform below in the thread👇)

Oded Rechavi

49,399 views • 2 months ago

HARD. RED. PILL. PT 2 As demonstrated in PT 1 of HARD. RED. PILL. (see above), the Khathars (also known as Khazarians), now called Catholics and still hard-and-fast believers in the de@th-cult Babylonian Mystery Religion, the ‘Father’ is actually Enki Lucifer, the serpent in the garden as mentioned of in the M@sonic King James Bible, and the ‘Father’s son’ is actually Marduk Lucifer Satain. The last name Satain comes from his/her mother/father hermaphrodite that Enki mated with that produced Marduk. These are incredibly wild claims that no devout Christian, C@tholic, or anyone else that refers to the KJ Bible as being supposedly the ‘word of God’ would ever believe, even for a minute. And that’s regardless of how much historic evidence were ever produced to back them up. That is, unless the claims came right out of the church’s mouth itself, making it simply not possible to deny. If this is what they are saying, only in Latin dialect so you can’t understand (remember, this is literally known as the Mystery Religion for a reason. Hiding the real truth is literally what it is all based on), then perhaps this would finally convince someone to understand that they had been lied to, and have tricked most of the people in the world into worshipping the very people you have referred to as ‘the devil’, all along. This is the really HARD. RED. PILL. to get down: they did. A few years ago churchgoers were stunned when during hymns, the words being sung indicated who the Papacy actually identifies as god the ‘Father’, and what was even more disturbing was the very next words of the hymn indicates that not only was everyone praying to the one entity they would never deliberately pray to, but the ‘baby Jesus’ was his/her son/daughter. Holy hell. Literally. The M@sonic bible was originally text from the Law of One, issued by the Oraphim Elohim who initiated the Human Elohim Project to begin with. This was a compendium of an extensive library of over 50 books that gave many examples of how to treat your neighbor as you would have them treat you, offering thousands of situations one may find themselves in that weren’t so black and white, and how a person might navigate those confusing waters while not trespassing against their brothers. The Khathars still had that library in their possession, and most of the peoples of the world were familiar with how wise and comprehensive the texts were that the real Jesheua Sananda Melchizedek would refer back to so often in his talks (not sermons and not offered in a religious manner, but as advice and wisdom). What the Khathars would have to do in order to trick the masses into joining the Mystery Religion, was to take a portion of that ancient and sacred text of knowledge and re-write it to their advantage. This meant they would have to integrate their own history from their 500,000 cuneiform clay texts of Babylon and weave the stories together to fool mankind into thinking this was Human history, and there was a creator god over all the peoples who loved mankind so much, that he had sent down his own son from the heavenly planes to atone for their ‘sins’. Up until that time, sin had not existed before. But how else would one convince basically all the people in the world that they needed the help of an overlord ‘god’ who was irrefutably ‘perfect’, if not to point out that Humans were conceived in sin? That they were ‘bad’ on a genetic level? Naturally no one ever bothered to ask the obvious question; how is it that if the ‘Father’ is perfect, could he have created billions of beings who were imperfect? The word perfect is an absurd lie. Nothing and no one is ever perfect. Even the most perfect creation always has room for improvement. That should be self-evident, just at a glance. MORE than this, ask the question how these imperfect beings were somehow responsible for the flaws that were inherent in their DNA cells and grey matter that they themselves didn’t create, but rather the ‘perfect’ Father had? And yet STILL MORE than just those questions, but HOW could the ‘Father’s’ son atone for all these pitiful beings wallowing in ‘sin’ BY BEING TORTURED TO DEATH? What kind of creator ‘Father’ would allow his own son to be tortured to death for any reason? Reptilian dragons would. Not an all-compassionate and loving creator, such as you were and still are. Not today, not yesterday, and not tomorrow. That would never happen. And even if for some reason, understandable only to the most confused and mentally ill asylum inmate, the creator god’s son COULD take on the burden of people’s ‘sins’ somehow when he wasn’t the one who ever committed those mortal crimes, how could DEATH be the logical answer of a totally innocent man? Of course none of this makes sense, but by smearing the threat of eternal damnation in a burning hell fire if you don’t believe it, you did. That’s literally the most overt definition of duress and blackmail anyone could ever dream up. The Jehovah Anunnaki ET hybrids’ history of invading Tara earth is not your history. Your history pre-dates the cuneiform clay texts of Sumer-Ur Babylon by nearly 560 million years. And it doesn’t involve you massing together to murder every man, woman and child in neighboring villages. Dragons do this, not Humans who were encoded to compassion and kindness from the outset of their avatar creation. Compare the stories in the Mesopotamian Enuma Elish clay texts of creation to your bible for yourself to see the flood is there, the parting of the Red Sea is there. They’re all there, and your copy is 250k years newer. In the video below, listen for yourself who the church claims is their god and who the ‘savior’ that ‘sacrificed himself for your sins’ happens to be. Because I can tell you right now, it isn’t Prime Creator and Jesheua Sandanda. This message will only be seen by your eyes if not shared, and if you want to reference this article again later, you will need to cut and paste it in your own notes off line, as it will surely be erased. This is the most accurate translation of these events I am aware of at this time.
2:22

HARD. RED. PILL. PT 2 As demonstrated in PT 1 of HARD. RED. PILL. (see above), the Khathars (also known as Khazarians), now called Catholics and still hard-and-fast believers in the de@th-cult Babylonian Mystery Religion, the ‘Father’ is actually Enki Lucifer, the serpent in the garden as mentioned of in the M@sonic King James Bible, and the ‘Father’s son’ is actually Marduk Lucifer Satain. The last name Satain comes from his/her mother/father hermaphrodite that Enki mated with that produced Marduk. These are incredibly wild claims that no devout Christian, C@tholic, or anyone else that refers to the KJ Bible as being supposedly the ‘word of God’ would ever believe, even for a minute. And that’s regardless of how much historic evidence were ever produced to back them up. That is, unless the claims came right out of the church’s mouth itself, making it simply not possible to deny. If this is what they are saying, only in Latin dialect so you can’t understand (remember, this is literally known as the Mystery Religion for a reason. Hiding the real truth is literally what it is all based on), then perhaps this would finally convince someone to understand that they had been lied to, and have tricked most of the people in the world into worshipping the very people you have referred to as ‘the devil’, all along. This is the really HARD. RED. PILL. to get down: they did. A few years ago churchgoers were stunned when during hymns, the words being sung indicated who the Papacy actually identifies as god the ‘Father’, and what was even more disturbing was the very next words of the hymn indicates that not only was everyone praying to the one entity they would never deliberately pray to, but the ‘baby Jesus’ was his/her son/daughter. Holy hell. Literally. The M@sonic bible was originally text from the Law of One, issued by the Oraphim Elohim who initiated the Human Elohim Project to begin with. This was a compendium of an extensive library of over 50 books that gave many examples of how to treat your neighbor as you would have them treat you, offering thousands of situations one may find themselves in that weren’t so black and white, and how a person might navigate those confusing waters while not trespassing against their brothers. The Khathars still had that library in their possession, and most of the peoples of the world were familiar with how wise and comprehensive the texts were that the real Jesheua Sananda Melchizedek would refer back to so often in his talks (not sermons and not offered in a religious manner, but as advice and wisdom). What the Khathars would have to do in order to trick the masses into joining the Mystery Religion, was to take a portion of that ancient and sacred text of knowledge and re-write it to their advantage. This meant they would have to integrate their own history from their 500,000 cuneiform clay texts of Babylon and weave the stories together to fool mankind into thinking this was Human history, and there was a creator god over all the peoples who loved mankind so much, that he had sent down his own son from the heavenly planes to atone for their ‘sins’. Up until that time, sin had not existed before. But how else would one convince basically all the people in the world that they needed the help of an overlord ‘god’ who was irrefutably ‘perfect’, if not to point out that Humans were conceived in sin? That they were ‘bad’ on a genetic level? Naturally no one ever bothered to ask the obvious question; how is it that if the ‘Father’ is perfect, could he have created billions of beings who were imperfect? The word perfect is an absurd lie. Nothing and no one is ever perfect. Even the most perfect creation always has room for improvement. That should be self-evident, just at a glance. MORE than this, ask the question how these imperfect beings were somehow responsible for the flaws that were inherent in their DNA cells and grey matter that they themselves didn’t create, but rather the ‘perfect’ Father had? And yet STILL MORE than just those questions, but HOW could the ‘Father’s’ son atone for all these pitiful beings wallowing in ‘sin’ BY BEING TORTURED TO DEATH? What kind of creator ‘Father’ would allow his own son to be tortured to death for any reason? Reptilian dragons would. Not an all-compassionate and loving creator, such as you were and still are. Not today, not yesterday, and not tomorrow. That would never happen. And even if for some reason, understandable only to the most confused and mentally ill asylum inmate, the creator god’s son COULD take on the burden of people’s ‘sins’ somehow when he wasn’t the one who ever committed those mortal crimes, how could DEATH be the logical answer of a totally innocent man? Of course none of this makes sense, but by smearing the threat of eternal damnation in a burning hell fire if you don’t believe it, you did. That’s literally the most overt definition of duress and blackmail anyone could ever dream up. The Jehovah Anunnaki ET hybrids’ history of invading Tara earth is not your history. Your history pre-dates the cuneiform clay texts of Sumer-Ur Babylon by nearly 560 million years. And it doesn’t involve you massing together to murder every man, woman and child in neighboring villages. Dragons do this, not Humans who were encoded to compassion and kindness from the outset of their avatar creation. Compare the stories in the Mesopotamian Enuma Elish clay texts of creation to your bible for yourself to see the flood is there, the parting of the Red Sea is there. They’re all there, and your copy is 250k years newer. In the video below, listen for yourself who the church claims is their god and who the ‘savior’ that ‘sacrificed himself for your sins’ happens to be. Because I can tell you right now, it isn’t Prime Creator and Jesheua Sandanda. This message will only be seen by your eyes if not shared, and if you want to reference this article again later, you will need to cut and paste it in your own notes off line, as it will surely be erased. This is the most accurate translation of these events I am aware of at this time.

W.R. Schock, QBD

47,075 views • 1 year ago

"Machinery really does exist. It's consciousness driven." ~Robert Bigelow Is Robert Bigelow a Firsthand Witness to Non-Human "Machinery"? (Not new but may have slipped under your radar. This is not the clip I was looking for but I watched it again and always wanted to share. ) Robert Bigelow: "You're leaving out, you know, kind of the holy grail of the topic. You know, machinery." George Knapp: "Yeah. Is there machinery? The New York Times reported that you modified your facility here in order to house some material from somewhere else." ~From that NYT article on 12/16/2017~ "Under Mr. Bigelow’s direction, the company modified buildings in Las Vegas for the storage of metal and other materials that Mr. Elizondo and program contractors said had been recovered from unidentified aerial phenomena." (helene cooper, Ralph Blumenthal and Leslie Kean received a lot of flack for that paragraph as people took it to mean that Bigelow (BAASS) received those materials/alloys. But that's not what they wrote. They modified buildings IN CASE they received that stuff. And we now know (or, have been told) that one of those "materials" was an alleged non-human craft from Lockheed Martin. Reportedly, they were trying to divest themselves of it due to a lack of success in reverse engineering efforts.) Link to full article: ~ Knapp: "Did you ever have it?" Bigelow: "We never had any." Knapp: "Did you ever see it?" (I transcribed Mr. B's answer word-for-word because he looked and sounded really uncomfortable answering. I have zero doubt he's telling the truth, but that doesn't mean ANY of this is proof that we have these craft.) Bigelow: "Umm. Well, I've...there's, I, umm... You know, do you see, do you see, uhh, things that are photos, or do you see things in person, and so forth? So, you don't want to, you don't want to talk about stuff in case it happens in the future." Knapp: "Yeah." (If Mr. Bigelow was shown government photos or videos (with proper provenance) of craft that were presented to him as being manufactured by non-humans or an intelligence of unknown origin, is that enough to call him a firsthand witness? If he saw "machinery" and saw it "in person," then he's 100% a firsthand witness. Did Lacatski take him to see the craft that was described in "Initial Revelations"? 👇🏼👇🏼👇🏼 ) “At the conclusion of a 2011 meeting in the Capitol building with a U.S. Senator and an agency Under Secretary, Lacatski, the only one of this book’s authors present, posed a question. He stated that the United States was in possession of a craft of unknown origin and had successfully gained access to its interior. This craft had a streamlined configuration suitable for aerodynamic flight but no intakes, exhaust, wings, or control surfaces. In fact, it appeared not to have an engine, fuel tanks, or fuel. Lacatski asked: What was the purpose of this craft? Was it a life-support craft useful only for atmospheric reentry or what? If it was a spacecraft, then how did it operate”? ~End Excerpt from Initial Revelations~ ~~~ Bigelow: "So, you don't want to, you don't want to talk about stuff in case it happens in the future. And...because who knows what might happen in terms of a coalescing of intersections that could happen? And so..." Knapp: "You don't wanna spill any beans that causes you, it puts you in a bad light somewhere down the road." Bigelow: "Well, I just, I, I, you know, of...I think that... Machinery really does exist. It does exist, you know? And so, but the problem has been the inability to back engineer. And I kind of think that some things require a weightless environment. So, part of that is, we don't have it here, terrestrially. So, what you need is a manufacturing facility where there's a weightless environment." Knapp: "It's part of the reason you developed Bigelow Aerospace." Bigelow: "For certain amalgams and certain kinds of things, but it's also like, you know, it doesn't do you much good to own a sliver of a case that holds a cell phone to understand, was it even a case? Was it holding something, and what was that something it was holding? And much less, how does a cell phone work? And, oh, by the way, it doesn't work at all if you don't have all the communication capabilities that that cell phone needs to communicate with, and all that kind of thing. So it's like...it could just domino out into a thousand different things. So, having an answer on a small sliver of something isn't necessarily much, right?" (On thing I've consistently said is: If we're going to wake up the masses, materials won't do it. A rectangular piece of metal from an alleged NHI craft that a scientist says cannot be manufactured on Earth with known technology, is interesting, but not enough. IMO, we need a full (or partial) craft (machinery) and bodies.) Bigelow: "So, we are embarrassingly - as a specie, as a science, as a space-faring, attempting specie - behind. We're a galactic embarrassment, almost. I mean, we're so far freaking behind, we really are. It's a galactic embarrassment and we may not even be able to, consciously, be able to operate the things, you know? Because it's not like fingerprints or anything, you know? It's consciousness driven. So you taste that a little bit in being able to have some communications." (If it's truly consciousness driven, then what jakebarber and Skywatcher have spoken about makes complete sense: Using telepathy or psi to attract/summon craft and then operate them from a distance.) Bigelow: "And we have other areas of psi and phenomenology, where mentally, people can have macro PK, you know? They can execute macro-PK events, and they're not supposed to be able to do that. Our physics and science says, 'No, you can't do that.' And yet it's happening, right? So whether it's Bob Jahn's and Brenda Dunne's work in micro PK on subatomic particles, or macro PK with Kulagina in Russia, and with her bell jar and all that kind of thing. And she's lifting a pencil or bottle cap." Here are a few clips of Kulagina. I'm not sure if she's done this under more strict controls. ( I love that Bigelow is well read on these subjects and knows they're legit. But I wonder when the masses will realize it?) ~~~ Bigelow: "You're sniffing at something that's really not on our radar as a parochial-educational system in physics or anything. You're totally outside the boundary, right? And we're still dealing with fire engines, right? Okay? So, it's really frustrating and the potential might some day be there to try to back engineer more. And we've heard stories about little bitty things that maybe the Russians have back engineered. "And so, we're still enough of, potentially, the Klingons to turn things into weapons, right? So that's a big problem. Is the fact that we don't have an intersection. If you have two lines, one on spirituality and technology. Where's the intersection ever happening? Because we're flatlined on spiritual evolution, but our technological evolution is not only vertical, it's segmented, it's jumping. It's jumping faster, you know? And so. where's that intersection of harmony supposed to be? I don't see it. I don't see it 100 years from now, or 200 years from now. I don't see anything on the horizon today that's saying, 'Well, the spirituality line is gonna start to really accelerate [and] this other one (technological) is going to start to stop. And eventually, there's going to be an intersection of harmony where there's an integration of the two. I don't see...I can't possibly foresee that, I don't see it at all. So it's a big worry." (Steven Greer has said: "The [ETs] that are here, they'd be like Gandhi. No civilization that is capable of interstellar travel is allowed out of their solar system until they're peaceful. Otherwise, they're quarantined. But actually, we have technology that can go interstellar. We're not allowed to. And the reason is, we're still savages." ~Greer on his IG (I have no idea if that's true and neither does Greer.) Bigelow: "If you were an occupying...if you were another specie on another planet, a thinking specie of intelligence, and we had the capabilities to get to you, you should be damn concerned about the human race." Knapp. "Yeah. If I had that technology, I would not give it to us." Bigelow: "Yeah! Okay, you just said it. That's exactly right. You just said that. That is the big enchilada, right there. You just said it, that's the plate." (I want this tech shared with the world if it can help clean up our planet or advance our science and medicine. But if it can be used as a weapon, it's hard to argue with what Mr. B and Knapp said there. This assumes we've been able to reverse engineer certain aspects of the tech we allegedly have in our possession.)
5:55

"Machinery really does exist. It's consciousness driven." ~Robert Bigelow Is Robert Bigelow a Firsthand Witness to Non-Human "Machinery"? (Not new but may have slipped under your radar. This is not the clip I was looking for but I watched it again and always wanted to share. ) Robert Bigelow: "You're leaving out, you know, kind of the holy grail of the topic. You know, machinery." George Knapp: "Yeah. Is there machinery? The New York Times reported that you modified your facility here in order to house some material from somewhere else." ~From that NYT article on 12/16/2017~ "Under Mr. Bigelow’s direction, the company modified buildings in Las Vegas for the storage of metal and other materials that Mr. Elizondo and program contractors said had been recovered from unidentified aerial phenomena." (helene cooper, Ralph Blumenthal and Leslie Kean received a lot of flack for that paragraph as people took it to mean that Bigelow (BAASS) received those materials/alloys. But that's not what they wrote. They modified buildings IN CASE they received that stuff. And we now know (or, have been told) that one of those "materials" was an alleged non-human craft from Lockheed Martin. Reportedly, they were trying to divest themselves of it due to a lack of success in reverse engineering efforts.) Link to full article: ~ Knapp: "Did you ever have it?" Bigelow: "We never had any." Knapp: "Did you ever see it?" (I transcribed Mr. B's answer word-for-word because he looked and sounded really uncomfortable answering. I have zero doubt he's telling the truth, but that doesn't mean ANY of this is proof that we have these craft.) Bigelow: "Umm. Well, I've...there's, I, umm... You know, do you see, do you see, uhh, things that are photos, or do you see things in person, and so forth? So, you don't want to, you don't want to talk about stuff in case it happens in the future." Knapp: "Yeah." (If Mr. Bigelow was shown government photos or videos (with proper provenance) of craft that were presented to him as being manufactured by non-humans or an intelligence of unknown origin, is that enough to call him a firsthand witness? If he saw "machinery" and saw it "in person," then he's 100% a firsthand witness. Did Lacatski take him to see the craft that was described in "Initial Revelations"? 👇🏼👇🏼👇🏼 ) “At the conclusion of a 2011 meeting in the Capitol building with a U.S. Senator and an agency Under Secretary, Lacatski, the only one of this book’s authors present, posed a question. He stated that the United States was in possession of a craft of unknown origin and had successfully gained access to its interior. This craft had a streamlined configuration suitable for aerodynamic flight but no intakes, exhaust, wings, or control surfaces. In fact, it appeared not to have an engine, fuel tanks, or fuel. Lacatski asked: What was the purpose of this craft? Was it a life-support craft useful only for atmospheric reentry or what? If it was a spacecraft, then how did it operate”? ~End Excerpt from Initial Revelations~ ~~~ Bigelow: "So, you don't want to, you don't want to talk about stuff in case it happens in the future. And...because who knows what might happen in terms of a coalescing of intersections that could happen? And so..." Knapp: "You don't wanna spill any beans that causes you, it puts you in a bad light somewhere down the road." Bigelow: "Well, I just, I, I, you know, of...I think that... Machinery really does exist. It does exist, you know? And so, but the problem has been the inability to back engineer. And I kind of think that some things require a weightless environment. So, part of that is, we don't have it here, terrestrially. So, what you need is a manufacturing facility where there's a weightless environment." Knapp: "It's part of the reason you developed Bigelow Aerospace." Bigelow: "For certain amalgams and certain kinds of things, but it's also like, you know, it doesn't do you much good to own a sliver of a case that holds a cell phone to understand, was it even a case? Was it holding something, and what was that something it was holding? And much less, how does a cell phone work? And, oh, by the way, it doesn't work at all if you don't have all the communication capabilities that that cell phone needs to communicate with, and all that kind of thing. So it's like...it could just domino out into a thousand different things. So, having an answer on a small sliver of something isn't necessarily much, right?" (On thing I've consistently said is: If we're going to wake up the masses, materials won't do it. A rectangular piece of metal from an alleged NHI craft that a scientist says cannot be manufactured on Earth with known technology, is interesting, but not enough. IMO, we need a full (or partial) craft (machinery) and bodies.) Bigelow: "So, we are embarrassingly - as a specie, as a science, as a space-faring, attempting specie - behind. We're a galactic embarrassment, almost. I mean, we're so far freaking behind, we really are. It's a galactic embarrassment and we may not even be able to, consciously, be able to operate the things, you know? Because it's not like fingerprints or anything, you know? It's consciousness driven. So you taste that a little bit in being able to have some communications." (If it's truly consciousness driven, then what jakebarber and Skywatcher have spoken about makes complete sense: Using telepathy or psi to attract/summon craft and then operate them from a distance.) Bigelow: "And we have other areas of psi and phenomenology, where mentally, people can have macro PK, you know? They can execute macro-PK events, and they're not supposed to be able to do that. Our physics and science says, 'No, you can't do that.' And yet it's happening, right? So whether it's Bob Jahn's and Brenda Dunne's work in micro PK on subatomic particles, or macro PK with Kulagina in Russia, and with her bell jar and all that kind of thing. And she's lifting a pencil or bottle cap." Here are a few clips of Kulagina. I'm not sure if she's done this under more strict controls. ( I love that Bigelow is well read on these subjects and knows they're legit. But I wonder when the masses will realize it?) ~~~ Bigelow: "You're sniffing at something that's really not on our radar as a parochial-educational system in physics or anything. You're totally outside the boundary, right? And we're still dealing with fire engines, right? Okay? So, it's really frustrating and the potential might some day be there to try to back engineer more. And we've heard stories about little bitty things that maybe the Russians have back engineered. "And so, we're still enough of, potentially, the Klingons to turn things into weapons, right? So that's a big problem. Is the fact that we don't have an intersection. If you have two lines, one on spirituality and technology. Where's the intersection ever happening? Because we're flatlined on spiritual evolution, but our technological evolution is not only vertical, it's segmented, it's jumping. It's jumping faster, you know? And so. where's that intersection of harmony supposed to be? I don't see it. I don't see it 100 years from now, or 200 years from now. I don't see anything on the horizon today that's saying, 'Well, the spirituality line is gonna start to really accelerate [and] this other one (technological) is going to start to stop. And eventually, there's going to be an intersection of harmony where there's an integration of the two. I don't see...I can't possibly foresee that, I don't see it at all. So it's a big worry." (Steven Greer has said: "The [ETs] that are here, they'd be like Gandhi. No civilization that is capable of interstellar travel is allowed out of their solar system until they're peaceful. Otherwise, they're quarantined. But actually, we have technology that can go interstellar. We're not allowed to. And the reason is, we're still savages." ~Greer on his IG (I have no idea if that's true and neither does Greer.) Bigelow: "If you were an occupying...if you were another specie on another planet, a thinking specie of intelligence, and we had the capabilities to get to you, you should be damn concerned about the human race." Knapp. "Yeah. If I had that technology, I would not give it to us." Bigelow: "Yeah! Okay, you just said it. That's exactly right. You just said that. That is the big enchilada, right there. You just said it, that's the plate." (I want this tech shared with the world if it can help clean up our planet or advance our science and medicine. But if it can be used as a weapon, it's hard to argue with what Mr. B and Knapp said there. This assumes we've been able to reverse engineer certain aspects of the tech we allegedly have in our possession.)

Joe Murgia

88,407 views • 1 year ago