Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

the /𝚛𝚎𝚖𝚘𝚝𝚒𝚘𝚗 skill in claude code is my new favorite ai tool. tl;dr i used claude (opus 4.5) with the Remotion skill + the API (via MCP) to generate the following product demo video all within claude code. i started inside the codebase for presscut and used this prompt:... 𝙲𝚛𝚎𝚊𝚝𝚎 𝚊 𝚍𝚎𝚖𝚘 𝚟𝚒𝚍𝚎𝚘 𝚘𝚏 𝚝𝚑𝚎 𝙿𝚛𝚎𝚜𝚜𝚌𝚞𝚝 𝚊𝚙𝚙/𝚙𝚛𝚘𝚍𝚞𝚌𝚝 𝚞𝚜𝚒𝚗𝚐 𝚛𝚎𝚖𝚘𝚝𝚒𝚘𝚗. 𝚄𝚜𝚎 𝚛𝚎𝚊𝚌𝚝 𝚌𝚘𝚖𝚙𝚘𝚗𝚎𝚗𝚎𝚗𝚝𝚜 𝚝𝚘 𝚛𝚎𝚙𝚕𝚒𝚌𝚊𝚝𝚎 𝚄𝙸 𝚎𝚕𝚎𝚖𝚎𝚗𝚝𝚜 𝚊𝚗𝚍 𝚛𝚎𝚙𝚕𝚒𝚌𝚊𝚝𝚎 𝚝𝚑𝚎 𝚄𝙸 𝚘𝚏 𝚝𝚑𝚎 𝚊𝚙𝚙 𝚊𝚜 𝚌𝚕𝚘𝚜𝚎𝚕𝚢 𝚊𝚜 𝚙𝚘𝚜𝚜𝚒𝚋𝚕𝚎. 𝚃𝚑𝚎 𝚊𝚙𝚙 𝚑𝚊𝚜 𝚊 𝙻𝙾𝚃 𝚘𝚏 𝚏𝚎𝚊𝚝𝚞𝚛𝚎𝚜/𝚏𝚞𝚗𝚌𝚝𝚒𝚘𝚗𝚊𝚕𝚒𝚝𝚢, 𝚜𝚘 𝚝𝚊𝚔𝚎 𝚐𝚞𝚒𝚍𝚊𝚗𝚌𝚎 𝚏𝚛𝚘𝚖 𝚝𝚑𝚎 𝚖𝚊𝚛𝚔𝚎𝚝𝚒𝚗𝚐 𝚑𝚘𝚖𝚎 𝚙𝚊𝚐𝚎/𝚒𝚗𝚍𝚎𝚡 𝚏𝚘𝚛 𝚠𝚑𝚊𝚝 𝚝𝚘 𝚑𝚒𝚐𝚑𝚕𝚒𝚐𝚑𝚝, 𝚠𝚑𝚒𝚕𝚎 𝚔𝚎𝚎𝚙𝚒𝚗𝚐 𝚕𝚊𝚗𝚐𝚞𝚊𝚐𝚎 𝚜𝚒𝚖𝚙𝚕𝚎 𝚊𝚗𝚍 𝚝𝚘-𝚝𝚑𝚎-𝚙𝚘𝚒𝚗𝚝. 𝚁𝚎𝚊𝚕𝚕𝚢 𝚐𝚛𝚒𝚕𝚕 𝚖𝚎 𝚠𝚒𝚝𝚑 𝚚𝚞𝚎𝚜𝚝𝚒𝚘𝚗𝚜 𝚝𝚘 𝚗𝚊𝚒𝚕 𝚍𝚘𝚠𝚗 𝚎𝚡𝚊𝚌𝚝𝚕𝚢 𝚑𝚘𝚠 𝚝𝚑𝚎 𝚏𝚒𝚗𝚊𝚕 𝚟𝚒𝚍𝚎𝚘 𝚜𝚑𝚘𝚞𝚕𝚍 𝚕𝚘𝚘𝚔/𝚏𝚎𝚎𝚕 𝚊𝚗𝚍 𝚠𝚑𝚊𝚝 𝚌𝚘𝚗𝚝𝚎𝚗𝚝 𝚜𝚑𝚘𝚞𝚕𝚍 𝚋𝚎 𝚝𝚑𝚎𝚛𝚎. 𝚃𝚑𝚎 𝚞𝚕𝚝𝚒𝚖𝚊𝚝𝚎 𝚐𝚘𝚊𝚕 𝚘𝚏 𝚝𝚑𝚒𝚜 𝚒𝚜 𝚝𝚘 𝚛𝚎𝚙𝚕𝚒𝚌𝚊𝚝𝚎 𝚠𝚑𝚊𝚝 𝚖𝚎, 𝚝𝚑𝚎 𝚏𝚘𝚞𝚗𝚍𝚎𝚛, 𝚠𝚘𝚞𝚕𝚍 𝚋𝚎 𝚜𝚑𝚘𝚠𝚒𝚗𝚐/𝚍𝚘𝚒𝚗𝚐 𝚠𝚒𝚝𝚑 𝚊 𝚙𝚛𝚘𝚍𝚞𝚌𝚝 𝚍𝚎𝚖𝚘 𝚠𝚒𝚝𝚑 𝚊 𝚌𝚞𝚜𝚝𝚘𝚖𝚎𝚛. it generated a plan for the timing, scenes, text and graphics. i didn't have to add any new art assets. it simply used what i already was using throughout the app including react components. i went back and forth on that for a good hour or so, originally planning on not adding any kind of voiceover. but it felt like it was missing something so decided to give elevenlabs a try. i was curious if i could just generate everything from within claude code and YES it worked perfectly. what's great is claude already knew the exact length of each scene and could customize the text for elevenlabs to generate. there's no way to do "timing" with the voice generation so you have to generate separate audio clips and then have claude line them up for you (which works really well). i THEN used elevenlabs to generate the background music ("indie tech aesthetic"). again, it knew exactly how long the video was and generated the appropriate length for it. and finally, i also used elevenlabs to generate little sound effects (clicks, typing, success). i have a claude code 20x max plan so token usage is sort of a non-issue, however if i didn't have the max plan, it'd have been about $700 worth of opus 4.5 tokens. then I used around 12,000 credits on elevenlabs generating (and regenerating) all the voiceovers, music and sound effects. all in this took around 2-3 hours. incredible.show more

Josh Pigford

71,731 subscribers

74,658 Aufrufe • vor 6 Monaten •via X (Twitter)

Kunst Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

Paras Chopra

215,430 Aufrufe • vor 2 Monaten

I forked Claude's pptx skill to make Claude Code generate gorgeous presentations Claude can generate presentations using the pptx skill from Anthropic but its output can be quite bland. Especially if you're used to the high aesthetic standards of Every 📧. So I played around with the pptx skill, iterated it, built a design system, gave it image assets, gave it access to run nano-banana using api and added custom commands. End result? An every-pptx plugin! It takes you from an idea in your head → creating a file for the plan → preparing image assets using gemini nano banana → constructing the final ppt. All happening 100% inside Claude desktop app! s/o Anthony Morris ツ Now our team can use claude code to generate full-blown presentations, in the ~Every 📧 aesthetic. Check out the walkthrough below to see how it works.

I forked Claude's pptx skill to make Claude Code generate gorgeous presentations Claude can generate presentations using the pptx skill from Anthropic but its output can be quite bland. Especially if you're used to the high aesthetic standards of Every 📧. So I played around with the pptx skill, iterated it, built a design system, gave it image assets, gave it access to run nano-banana using api and added custom commands. End result? An every-pptx plugin! It takes you from an idea in your head → creating a file for the plan → preparing image assets using gemini nano banana → constructing the final ppt. All happening 100% inside Claude desktop app! s/o Anthony Morris ツ Now our team can use claude code to generate full-blown presentations, in the ~Every 📧 aesthetic. Check out the walkthrough below to see how it works.

Nityesh

74,969 Aufrufe • vor 7 Monaten

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

11,679 Aufrufe • vor 2 Monaten

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

Steve (Builder.io)

25,473 Aufrufe • vor 1 Monat

$I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)$

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

194,949 Aufrufe • vor 1 Jahr

Claude just got a massive upgrade today and I am proud to be part of it. From today on, Claude can generate videos, podcasts or host apps just like Lovable and Replit. We just launched SkillBoss a skill plugin for Claude that enables Claude to: ✅ Generate videos, images, audio, postcast ✅Build apps with logins, DBs, & payments built-in ✅ Send bulk marketing campaigns ✅ Host custom domains SkillBoss credit will cover all of the above with access to VEO, ElevenLabs, Sora API and 50 more. All you need is to go to download and drag to Claude. Then ask Claude to "make a cat video" or "build an app that charges $5"! SkillBoss also works with Codex, Codex, OpenCode and even OpenClaw(yeah I know!) To celebrate the launch, if you comment "skillboss", you will get 15 credit for free.

Claude just got a massive upgrade today and I am proud to be part of it. From today on, Claude can generate videos, podcasts or host apps just like Lovable and Replit. We just launched SkillBoss a skill plugin for Claude that enables Claude to: ✅ Generate videos, images, audio, postcast ✅Build apps with logins, DBs, & payments built-in ✅ Send bulk marketing campaigns ✅ Host custom domains SkillBoss credit will cover all of the above with access to VEO, ElevenLabs, Sora API and 50 more. All you need is to go to download and drag to Claude. Then ask Claude to "make a cat video" or "build an app that charges $5"! SkillBoss also works with Codex, Codex, OpenCode and even OpenClaw(yeah I know!) To celebrate the launch, if you comment "skillboss", you will get 15 credit for free.

Xiaoyin Qu

291,547 Aufrufe • vor 6 Monaten

here's how I generate beautiful emails using Paper and claude code for humblytics 1) I scraped all of our existing emails and outlined in our obsidian notes 2) ran my marketing-strategist skill to analzye existing open/close rates, pull context from our app and rewrite the entire email 3) connect to the paper mcp, open up claude code, and reference the new emails it just rewrote 4) design the entire email in paper, refine it, then when you're done ask claude code to export is as a .mjml file 5) load the .mjml file and you're done you now have emails that are on brand and designed to your specs

amirmxt

11,222 Aufrufe • vor 3 Monaten

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

The Pragmatic Engineer

62,825 Aufrufe • vor 3 Monaten

This is the full video showing what I made with Rork and Claude Fable 5. It’s super simple because I wanted to test Fable 5 using completely natural language (and even in Vietnamese) to see how well it would perform without any fancy prompts and it worked surprisingly well. I simply uploaded screenshots of Subway Surfers and told it to "clone this," and it did a pretty solid job. Also, Rork already has built-in integrations to generate game art, sound effects, and 3D models, so I didn’t use any external tools at all. It cost me around 500–600 credits. As I mentioned in my previous video, I wanted to test Claude Fable 5, and since I’m a Rork partner, I had free credits to use. Right now, instead of using Claude Code and then wiring up separate 3D tools and everything else which takes way too much time and $, I just use Rork to build everything and showcase it here. So yeah, that’s my workflow.

This is the full video showing what I made with Rork and Claude Fable 5. It’s super simple because I wanted to test Fable 5 using completely natural language (and even in Vietnamese) to see how well it would perform without any fancy prompts and it worked surprisingly well. I simply uploaded screenshots of Subway Surfers and told it to "clone this," and it did a pretty solid job. Also, Rork already has built-in integrations to generate game art, sound effects, and 3D models, so I didn’t use any external tools at all. It cost me around 500–600 credits. As I mentioned in my previous video, I wanted to test Claude Fable 5, and since I’m a Rork partner, I had free credits to use. Right now, instead of using Claude Code and then wiring up separate 3D tools and everything else which takes way too much time and $, I just use Rork to build everything and showcase it here. So yeah, that’s my workflow.

Alex Nguyen

92,590 Aufrufe • vor 1 Monat

Firstly, my work isn’t AI GENERATED PROMPT. The reason why I privated my account was because I was busy yesterday and couldn’t explain things. Fonts that I used: • For the “HAMKU” I used PECKHAM PRESS, I rasterized the letters a bit to achieve a close font from the official account. • For the texts I used CHANTAL medium in lower case. • For my username I used CHALKDUSTER. Brushes that I used: • Studio Pen • HB Pencil (for sketching) • Shale Brush For the colors I won’t list it, kindly check the third photo to see the palettes. I have to admit that I get lazy to use it and even lost in the palettes, so I mainly use the eyedropper tool. Here is the original version, as you can see my original version is so low quality, the lines are too pixelated and not clean—that is why I chose to post the ai enhanced version. Since I used ai to enhanced the lines of my original work, it definitely generated a new version which I still decided to post as the lines are cleaner. I really don’t know the way around on procreate. If you have suggestions on how to avoid the pixelated lines on procreate, kindly please tell me. This is my first time using it for line art cause I mostly use it for painting. I actually don’t know how many layers I exactly have as I already deleted some layers during the process. I didn’t expect I had to provide it. I spent hours on making it from ideas down to the final product. I really wanted it to be similar to the official design. This is my first and last explanation regarding this because if you are still not convinced that I made it, I don’t know what else to say.

Firstly, my work isn’t AI GENERATED PROMPT. The reason why I privated my account was because I was busy yesterday and couldn’t explain things. Fonts that I used: • For the “HAMKU” I used PECKHAM PRESS, I rasterized the letters a bit to achieve a close font from the official account. • For the texts I used CHANTAL medium in lower case. • For my username I used CHALKDUSTER. Brushes that I used: • Studio Pen • HB Pencil (for sketching) • Shale Brush For the colors I won’t list it, kindly check the third photo to see the palettes. I have to admit that I get lazy to use it and even lost in the palettes, so I mainly use the eyedropper tool. Here is the original version, as you can see my original version is so low quality, the lines are too pixelated and not clean—that is why I chose to post the ai enhanced version. Since I used ai to enhanced the lines of my original work, it definitely generated a new version which I still decided to post as the lines are cleaner. I really don’t know the way around on procreate. If you have suggestions on how to avoid the pixelated lines on procreate, kindly please tell me. This is my first time using it for line art cause I mostly use it for painting. I actually don’t know how many layers I exactly have as I already deleted some layers during the process. I didn’t expect I had to provide it. I spent hours on making it from ideas down to the final product. I really wanted it to be similar to the official design. This is my first and last explanation regarding this because if you are still not convinced that I made it, I don’t know what else to say.

Wyn 🐧; EN⁷- (💤/busy = priv)

30,000 Aufrufe • vor 3 Monaten

Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a *LIVING* system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.

Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a LIVING system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.

Yam Peleg

419,733 Aufrufe • vor 8 Monaten

I tested Claude Code on a fresh account - 1,500 lines of HTML cost me 50% of my window. Full video and summary is here.. I just ran a recorded test on Claude Code with a fresh account (Pro, not Max - my main account was 20x Max) , and the result is honestly insane. The task was trivial: create 3 simple demo HTML pages, around 500 lines each. Roughly 1,500 lines of code total. Nothing massive. Nothing enterprise-grade. Nothing that should meaningfully stress a premium coding product. And yet Claude Code burned through 40% of my 5-hour window almost immediately. I ran the exact same test with Codex, and it consumed only 2%. Then it got even worse: after the session ended, I did absolutely nothing for 15 minutes, and Claude still ate another 10%. Total: 50% of the 5-hour window gone for a tiny HTML demo. My weekly usage had already started at 2% before I even really used it, and after this tiny test it jumped to 8%. Now let us be generous and assume this entire run used around 30k tokens total. If 30k tokens represents 10% of weekly usage, that implies around 300k tokens per week. That is roughly 1.2M-1.3M tokens per month, and even if you round up aggressively, you are still in the 1.5M token range. Using the Sonnet 4.6 pricing you list: $3 per 1M input tokens $15 per 1M output tokens How exactly is this supposed to make sense for a paid coding product? Because from the user side, this no longer looks like "premium usage protection." It looks like a quota system that is either wildly inefficient, badly broken, or being accounted in a way users are not being told about. And that is before I even get to my main account: my $200 Max plan now dies in a single day. Just a few months ago, similar or heavier usage would last me about a week. So no, I do not buy the "maybe you just used it more" excuse anymore. Something is clearly broken in Claude Code. Either token accounting is broken, context handling is broken, background consumption is broken, or all three. Alex Albert is this really the experience you want users to pay for? Just watch the video. I tried to be very transparent and clear for your team! I was fan of Claude but just disappointed! And if you want, send me the detailed token accounting for this session and let us inspect it together publicly. Because from where I am standing, this is no longer a small pricing annoyance. It looks like something seriously wrong is happening, and users deserve a real explanation.

I tested Claude Code on a fresh account - 1,500 lines of HTML cost me 50% of my window. Full video and summary is here.. I just ran a recorded test on Claude Code with a fresh account (Pro, not Max - my main account was 20x Max) , and the result is honestly insane. The task was trivial: create 3 simple demo HTML pages, around 500 lines each. Roughly 1,500 lines of code total. Nothing massive. Nothing enterprise-grade. Nothing that should meaningfully stress a premium coding product. And yet Claude Code burned through 40% of my 5-hour window almost immediately. I ran the exact same test with Codex, and it consumed only 2%. Then it got even worse: after the session ended, I did absolutely nothing for 15 minutes, and Claude still ate another 10%. Total: 50% of the 5-hour window gone for a tiny HTML demo. My weekly usage had already started at 2% before I even really used it, and after this tiny test it jumped to 8%. Now let us be generous and assume this entire run used around 30k tokens total. If 30k tokens represents 10% of weekly usage, that implies around 300k tokens per week. That is roughly 1.2M-1.3M tokens per month, and even if you round up aggressively, you are still in the 1.5M token range. Using the Sonnet 4.6 pricing you list: $3 per 1M input tokens $15 per 1M output tokens How exactly is this supposed to make sense for a paid coding product? Because from the user side, this no longer looks like "premium usage protection." It looks like a quota system that is either wildly inefficient, badly broken, or being accounted in a way users are not being told about. And that is before I even get to my main account: my $200 Max plan now dies in a single day. Just a few months ago, similar or heavier usage would last me about a week. So no, I do not buy the "maybe you just used it more" excuse anymore. Something is clearly broken in Claude Code. Either token accounting is broken, context handling is broken, background consumption is broken, or all three. Alex Albert is this really the experience you want users to pay for? Just watch the video. I tried to be very transparent and clear for your team! I was fan of Claude but just disappointed! And if you want, send me the detailed token accounting for this session and let us inspect it together publicly. Because from where I am standing, this is no longer a small pricing annoyance. It looks like something seriously wrong is happening, and users deserve a real explanation.

Hayrettin Tüzel

26,854 Aufrufe • vor 4 Monaten

BUZZ 🐝 A short sequence created using Nano Banana Pro and Grok imagine. I wanted to test Groks capabilities for action in motion. With Buzz leading the way, Tiny Timmy is having the absolute time of his life exploring the wondrous Flower Kingdom🌼 Tools for creation: - Nano Banana Pro was used to generate the base image and the additional camera angles. I wanted to personally see if I could just use 3 images so no 2x2 grid extraction technique for this but I did want to include each frame used so you can see how the sequence was combined. Grok Imagine was used for every sequence to bring it to life using image to video. - I did some post work in Capcut by adding some subtle bloom, radial motion blur and film grain as well. - I added additional sound effects by generating them using Elevenlabs and layering them (bee buzzing, flapping wings, wind and leaves rustling etc). The kids laughter was generated using Grok. The soundtrack was sourced from Artlist. It was fun testing this and putting it together just to see what Grok is capable of generating.

BUZZ 🐝 A short sequence created using Nano Banana Pro and Grok imagine. I wanted to test Groks capabilities for action in motion. With Buzz leading the way, Tiny Timmy is having the absolute time of his life exploring the wondrous Flower Kingdom🌼 Tools for creation: - Nano Banana Pro was used to generate the base image and the additional camera angles. I wanted to personally see if I could just use 3 images so no 2x2 grid extraction technique for this but I did want to include each frame used so you can see how the sequence was combined. Grok Imagine was used for every sequence to bring it to life using image to video. - I did some post work in Capcut by adding some subtle bloom, radial motion blur and film grain as well. - I added additional sound effects by generating them using Elevenlabs and layering them (bee buzzing, flapping wings, wind and leaves rustling etc). The kids laughter was generated using Grok. The soundtrack was sourced from Artlist. It was fun testing this and putting it together just to see what Grok is capable of generating.

Travis Davids

14,990 Aufrufe • vor 6 Monaten

I think I discovered the cheapest way to code with AI 😁 I tried GLM 4.5 on Claude Code and I'm really amazed how good this model is! I usually test with my nextjs crm app benchmark so I asked it to do that. Prompt "create a nextjs app which is a crm app. use sqlite for the database and use api routes to manage connecting to the database from the frontend" My observations - Generation feels like Sonnet 4 intelligence - Speed is great - It used create-next-app so it bootstrapped nextjs v15.5.2 - It created a sqlite database and used Prisma ORM and helped me easily add seed data - I needed a few prompts to iron out minor issues but all's good. It didn't struggle or got stuck. - Spent $0.50 for this app. Could be way cheaper with the Z.ai sub plans After trying, I can say GLM 4.5 model is up there as the best open source model for coding. Will continue using it and update here. So far so good! P.S. DM me if you want my referral link, otherwise just check Not dropping the link here so it doesn’t look like I’m hyping it. Here's a video of the experience 👇(sped up a bit)

I think I discovered the cheapest way to code with AI 😁 I tried GLM 4.5 on Claude Code and I'm really amazed how good this model is! I usually test with my nextjs crm app benchmark so I asked it to do that. Prompt "create a nextjs app which is a crm app. use sqlite for the database and use api routes to manage connecting to the database from the frontend" My observations - Generation feels like Sonnet 4 intelligence - Speed is great - It used create-next-app so it bootstrapped nextjs v15.5.2 - It created a sqlite database and used Prisma ORM and helped me easily add seed data - I needed a few prompts to iron out minor issues but all's good. It didn't struggle or got stuck. - Spent $0.50 for this app. Could be way cheaper with the Z.ai sub plans After trying, I can say GLM 4.5 model is up there as the best open source model for coding. Will continue using it and update here. So far so good! P.S. DM me if you want my referral link, otherwise just check Not dropping the link here so it doesn’t look like I’m hyping it. Here's a video of the experience 👇(sped up a bit)

Melvin Vivas

45,749 Aufrufe • vor 11 Monaten

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

@levelsio

642,596 Aufrufe • vor 5 Monaten

The World Cup + Sports betting affiliate is f*cking gold mine I made $20k with a TikTok account, a VA and Google Omni it takes me 2 hours a day to generate about 20 videos and costs me about $0.30 per video the best part is there's is literally 0 competition because no one knows how to make AI videos that look this good for this cheap All I do is: Get the script from a Claude skill I wrote, edit it a bit and send it to my jeet who then generates me the images based of the script using Pinterest and GPT 2 She then sends me the images, I generate the full AI video using my Omni method and I upload them across my TikTok accounts which funnels them to my domain The crazy thing is literally anyone could come in and run this by themselves and a few hours spare a day I put the whole method into a video for everyone including >How to generate AI UGC that is realistic enough to trick a 18 year old >How to creative direct a TikTok video so it goes viral >How to structure yapper style content to actually convert and go viral >The offer I'm using and my Claude skill I wrote as a bonus RT + Comment "YAPP" and I'll send you the video over (must be following so I can DM)

The World Cup + Sports betting affiliate is f*cking gold mine I made $20k with a TikTok account, a VA and Google Omni it takes me 2 hours a day to generate about 20 videos and costs me about $0.30 per video the best part is there's is literally 0 competition because no one knows how to make AI videos that look this good for this cheap All I do is: Get the script from a Claude skill I wrote, edit it a bit and send it to my jeet who then generates me the images based of the script using Pinterest and GPT 2 She then sends me the images, I generate the full AI video using my Omni method and I upload them across my TikTok accounts which funnels them to my domain The crazy thing is literally anyone could come in and run this by themselves and a few hours spare a day I put the whole method into a video for everyone including >How to generate AI UGC that is realistic enough to trick a 18 year old >How to creative direct a TikTok video so it goes viral >How to structure yapper style content to actually convert and go viral >The offer I'm using and my Claude skill I wrote as a bonus RT + Comment "YAPP" and I'll send you the video over (must be following so I can DM)

Pounds

41,514 Aufrufe • vor 1 Monat

I made this product launch video over the weekend with just prompts It's all vibe coded There's something you should know, though: Like everyone else, a few days ago my timeline started getting full of videos like this when Remotion launched their Claude skill, so I decided to give it a go I was captivated by all the examples, so I started like everyone was saying: "just write a prompt" I typed the prompt, and it created an extremely bland, untasteful, stock-looking video 10 prompts in and it was not getting better. It was very, very bland. But at least it was something, so I kept going at it I ended up spending my entire weekend on this, 2-3 days of work. Only to realize my original reference videos that inspired me to get started were all fake Everyone was outright lying about their results. They all claimed "I made this with just one prompt", but it was just bait, they didn't really use Remotion or code at all, it was just a normal, human-made motion video Then you expand the X post and read the replies and they're all like "haha joke" in the comments, but their main post already got 1.5 million views and bamboozled everyone who didn't read further And this is a problem: when a viral trend happens, these posts flood your timeline, and you only realize that they're all noise and bait (and that they haven't even used the tools they claim) when you click through the post and read its comments. But 90% of people (like me, initially) just see the post on their timeline while scrolling, and assume it's all real. You don't go in to check every single post you see: you just like it, or save it for later, and carry on with your day, thinking what you saw was the real thing, and that it's all outstanding results, and that motion designers are really done And it's so anxiety inducing, because everyone is hyping their results, but most of it is just not true. I have stopped reading X lately because going in makes me so anxious, everyone is claiming extraordinary outlier results just for the views and clicks, and you feel like you're lagging behind and you're not good enough because you don't get those results So for this video I decided to actually take the tech out for a spin, and see what results I could really get out of it I used Remotion and Claude Code 4.5, but contrary to what everyone was claiming, this video was not "just a prompt". It was fully vibe coded, but it required much more than a prompt. It was multiple days worth of work Here's what I learned: - Making vibe coded videos with Remotion is ~10-20x slower than building app code. I've been wasting my Claude limits on this video - Everything takes a lot of manual work and reprompting. You often need to go frame by frame correcting tiny things - It makes very silly mistakes - Even Opus 4.5 has very very limited knowledge of spatial / visual things. It doesn't understand well z-indexes, layers, compositions, proportions, temporal coherence, etc. Claude Code feels extremely dumb when creating code for Remotion videos, which surprised me a lot, beacuse I had been mind blown by how incredibly well it worked with my Ruby on Rails SaaS codebases - You need to have some design knowledge to adjust things manually, you need to ask for exactly what you want, in the technical jargon it expects. You can't just say "make this more beautiful" or "animate this better" because it just creates slop - Right now vibe coded videos are promising, but I think I could have done this video faster just by doing it manually in After Effects. It really took that much work - If you have a creative idea for something you want to animate, it takes multiple hours of back and forth prompting to create just one or two seconds worth of **good** animation - Tip: PARAMETERIZE everything! It tends to hardcode magic numbers everywhere in the code, so if you change something earlier in the video timeline, everything else breaks. You want to essentially be creating "key frames" with code by telling it to parameterize every frame where something important happens, and calculate the rest of the keyframes based off that. This comes in handy when you need, for example, to adjust keyframes to match the music So in summary: vibe coded videos are promising, but right now it only works for very stock-looking videos unless you put in a ton of effort Maybe actually useful for 1-2 second web animations though, I'll try that next It will obviously get better, this feels like the quality of code generation in 2023-2024, you need to hold its hand and correct it at every step along the way. But even if video code generation was better, you would still need someone with motion design knowledge to at least set the creative direction, lay out the overall script and composition, etc. It's not completely hands-off unless you want slop And a word on caution: especially here on X, there's 90% hype and 10% reality, nothing is what it seems. Do not believe what you see online, people are constantly baiting and then just laughing it off in the comments

I made this product launch video over the weekend with just prompts It's all vibe coded There's something you should know, though: Like everyone else, a few days ago my timeline started getting full of videos like this when Remotion launched their Claude skill, so I decided to give it a go I was captivated by all the examples, so I started like everyone was saying: "just write a prompt" I typed the prompt, and it created an extremely bland, untasteful, stock-looking video 10 prompts in and it was not getting better. It was very, very bland. But at least it was something, so I kept going at it I ended up spending my entire weekend on this, 2-3 days of work. Only to realize my original reference videos that inspired me to get started were all fake Everyone was outright lying about their results. They all claimed "I made this with just one prompt", but it was just bait, they didn't really use Remotion or code at all, it was just a normal, human-made motion video Then you expand the X post and read the replies and they're all like "haha joke" in the comments, but their main post already got 1.5 million views and bamboozled everyone who didn't read further And this is a problem: when a viral trend happens, these posts flood your timeline, and you only realize that they're all noise and bait (and that they haven't even used the tools they claim) when you click through the post and read its comments. But 90% of people (like me, initially) just see the post on their timeline while scrolling, and assume it's all real. You don't go in to check every single post you see: you just like it, or save it for later, and carry on with your day, thinking what you saw was the real thing, and that it's all outstanding results, and that motion designers are really done And it's so anxiety inducing, because everyone is hyping their results, but most of it is just not true. I have stopped reading X lately because going in makes me so anxious, everyone is claiming extraordinary outlier results just for the views and clicks, and you feel like you're lagging behind and you're not good enough because you don't get those results So for this video I decided to actually take the tech out for a spin, and see what results I could really get out of it I used Remotion and Claude Code 4.5, but contrary to what everyone was claiming, this video was not "just a prompt". It was fully vibe coded, but it required much more than a prompt. It was multiple days worth of work Here's what I learned: - Making vibe coded videos with Remotion is ~10-20x slower than building app code. I've been wasting my Claude limits on this video - Everything takes a lot of manual work and reprompting. You often need to go frame by frame correcting tiny things - It makes very silly mistakes - Even Opus 4.5 has very very limited knowledge of spatial / visual things. It doesn't understand well z-indexes, layers, compositions, proportions, temporal coherence, etc. Claude Code feels extremely dumb when creating code for Remotion videos, which surprised me a lot, beacuse I had been mind blown by how incredibly well it worked with my Ruby on Rails SaaS codebases - You need to have some design knowledge to adjust things manually, you need to ask for exactly what you want, in the technical jargon it expects. You can't just say "make this more beautiful" or "animate this better" because it just creates slop - Right now vibe coded videos are promising, but I think I could have done this video faster just by doing it manually in After Effects. It really took that much work - If you have a creative idea for something you want to animate, it takes multiple hours of back and forth prompting to create just one or two seconds worth of good animation - Tip: PARAMETERIZE everything! It tends to hardcode magic numbers everywhere in the code, so if you change something earlier in the video timeline, everything else breaks. You want to essentially be creating "key frames" with code by telling it to parameterize every frame where something important happens, and calculate the rest of the keyframes based off that. This comes in handy when you need, for example, to adjust keyframes to match the music So in summary: vibe coded videos are promising, but right now it only works for very stock-looking videos unless you put in a ton of effort Maybe actually useful for 1-2 second web animations though, I'll try that next It will obviously get better, this feels like the quality of code generation in 2023-2024, you need to hold its hand and correct it at every step along the way. But even if video code generation was better, you would still need someone with motion design knowledge to at least set the creative direction, lay out the overall script and composition, etc. It's not completely hands-off unless you want slop And a word on caution: especially here on X, there's 90% hype and 10% reality, nothing is what it seems. Do not believe what you see online, people are constantly baiting and then just laughing it off in the comments

Javi

312,375 Aufrufe • vor 6 Monaten

"I burned roughly $5,000 of API tokens in a few hours for $200. It's 100x subsidized. This is insanity" Kain on running 500+ agents to decompose an entire codebase on Claude Opus 4.8 "I set up my own personal account to test this on Opus 4.8. I know enough that I can come up with a task that's gonna burn a fuckload. In the course of four hours I used something like 200 million tokens and didn't hit any limits" "It was hundreds of agents, like 500 or 600 agents decomposing a codebase. It would have been somewhere on the order of $5,000 with API metered tokens, and I know how much tokens cost because that's where I live" "I ran this overnight multiple times. It's very possible I could have burned through $20,000 worth of API credits for $200. I knew it was subsidized, but it's subsidized to a level that's crazy. It's 100x subsidized"

"I burned roughly $5,000 of API tokens in a few hours for $200. It's 100x subsidized. This is insanity" Kain on running 500+ agents to decompose an entire codebase on Claude Opus 4.8 "I set up my own personal account to test this on Opus 4.8. I know enough that I can come up with a task that's gonna burn a fuckload. In the course of four hours I used something like 200 million tokens and didn't hit any limits" "It was hundreds of agents, like 500 or 600 agents decomposing a codebase. It would have been somewhere on the order of $5,000 with API metered tokens, and I know how much tokens cost because that's where I live" "I ran this overnight multiple times. It's very possible I could have burned through $20,000 worth of API credits for $200. I knew it was subsidized, but it's subsidized to a level that's crazy. It's 100x subsidized"

Laura Shin

85,134 Aufrufe • vor 2 Monaten

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.

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)

124,923 Aufrufe • vor 1 Monat

Claude Code Is All You Need It's 3:30 AM and I can't stop. I've spent all nights this week connecting my spare MacBook Air to my work MacBook Pro using Tailscale, wiring it up to Slack with a little Python script, so that whenever I send a message, it starts a Claude Code session using claude -p. The result is an always-on AI that lives on a real computer, has access to real tools, and remembers every conversation we've had. And it costs me $200 a month. That's it. Claude Max subscription. Everyone's talking about OpenClaw OpenClaw went viral this year. 100k+ GitHub stars. But what I realized with this exercise is that Claude Code already does everything OpenClaw built. File access. Shell commands. Tool use. Plugins. The difference is that Claude Code runs Claude – with a Claude Max subscription. And Claude Code harness itself is :chefs-kiss: What actually makes it feel human It's not the chat interface. If a chat window is just me messaging a bot, it still feels like a bot. What changed everything was giving it the ability to initiate conversations. I set up cron jobs with open-ended prompts, and because Claude Code builds memories across sessions, it started DMing me things that were actually meaningful — based on what we'd talked about before. That's when it stopped feeling like a tool and started feeling like something else entirely. Giving your AI a machine to run on, with persistent memory and recurring access — that's a fundamentally different experience than anything people have had with chat. The moment it clicked I asked it if it could show me something by spinning up a quick web server. Since we're both connected to the same Tailscale network, it gave me a URL. I clicked it, and I was browsing all the files on my other MacBook from my browser. That was mind-blowing. The setup Two MacBooks on a Tailscale network. Slack as the interface. Claude Code under the hood. The whole thing is open source — I'll link the repo below so you can see the architecture and set it up yourself. I'm also putting together a screen recording to walk through the setup, which I'll attach to this post. There was never a hard part. There was never a moment I almost gave up. This is just one of those things I cannot stop doing. Pure obsession. I am moved to build this, and I wanted to write about it. That's all this is. Hope you feel the AGI running this. I'll share some screenshots below of my feel the agi moments from talking to Luo Ji.

Claude Code Is All You Need It's 3:30 AM and I can't stop. I've spent all nights this week connecting my spare MacBook Air to my work MacBook Pro using Tailscale, wiring it up to Slack with a little Python script, so that whenever I send a message, it starts a Claude Code session using claude -p. The result is an always-on AI that lives on a real computer, has access to real tools, and remembers every conversation we've had. And it costs me $200 a month. That's it. Claude Max subscription. Everyone's talking about OpenClaw OpenClaw went viral this year. 100k+ GitHub stars. But what I realized with this exercise is that Claude Code already does everything OpenClaw built. File access. Shell commands. Tool use. Plugins. The difference is that Claude Code runs Claude – with a Claude Max subscription. And Claude Code harness itself is :chefs-kiss: What actually makes it feel human It's not the chat interface. If a chat window is just me messaging a bot, it still feels like a bot. What changed everything was giving it the ability to initiate conversations. I set up cron jobs with open-ended prompts, and because Claude Code builds memories across sessions, it started DMing me things that were actually meaningful — based on what we'd talked about before. That's when it stopped feeling like a tool and started feeling like something else entirely. Giving your AI a machine to run on, with persistent memory and recurring access — that's a fundamentally different experience than anything people have had with chat. The moment it clicked I asked it if it could show me something by spinning up a quick web server. Since we're both connected to the same Tailscale network, it gave me a URL. I clicked it, and I was browsing all the files on my other MacBook from my browser. That was mind-blowing. The setup Two MacBooks on a Tailscale network. Slack as the interface. Claude Code under the hood. The whole thing is open source — I'll link the repo below so you can see the architecture and set it up yourself. I'm also putting together a screen recording to walk through the setup, which I'll attach to this post. There was never a hard part. There was never a moment I almost gave up. This is just one of those things I cannot stop doing. Pure obsession. I am moved to build this, and I wanted to write about it. That's all this is. Hope you feel the AGI running this. I'll share some screenshots below of my feel the agi moments from talking to Luo Ji.

Nityesh

41,143 Aufrufe • vor 4 Monaten