Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Every JavaScript dev has done this at least once: > Typed ${name} inside "quotes"... > Hit save. > Saw "Hello ${name}" instead of Hello John. > Then sighed, deleted, and retyped everything with backticks. So I built "Quotick", a VS Code extension that instantly converts quotes → backticks the... show more

Kartik

9,503 subscribers

100,031 görüntüleme • 9 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

Milind S

12,334 görüntüleme • 25 gün önce

Alibaba just dropped a free AI that codes like a $150/hr developer. And it runs on your laptop. Qwen 3 Coder Next has 80 billion parameters but only uses 3 billion at a time. So you get massive model power with tiny model speed. The real kicker? It handles 256,000 tokens of context. That's your entire codebase. Every file. All at once. People are building 2D games in seconds. Full IDE integrations that write, test, and fix code automatically. Custom business tools without hiring devs. It works with OpenClaw, Claude Code, and every major coding tool. No complicated setup. Just download and go. Completely open source. Zero API queues. You own it. Your competitors are using this right now.

Alibaba just dropped a free AI that codes like a $150/hr developer. And it runs on your laptop. Qwen 3 Coder Next has 80 billion parameters but only uses 3 billion at a time. So you get massive model power with tiny model speed. The real kicker? It handles 256,000 tokens of context. That's your entire codebase. Every file. All at once. People are building 2D games in seconds. Full IDE integrations that write, test, and fix code automatically. Custom business tools without hiring devs. It works with OpenClaw, Claude Code, and every major coding tool. No complicated setup. Just download and go. Completely open source. Zero API queues. You own it. Your competitors are using this right now.

Julian Goldie SEO

30,259 görüntüleme • 5 ay önce

$THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this$

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

55,345 görüntüleme • 1 ay önce

We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 sec), instantly forgetting what just happened. We pushed to 3 orders of magnitude beyond SOTA. Introducing RoboTTT. Test-Time Training (“TTT”) carries a tiny model *inside* the model. Every incoming sensor reading triggers one gradient step on that tiny core, so the history keeps getting compressed into its weights. The hidden state has a fixed size (literally a small neural net), so the robot can “grok” arbitrarily long experience with little overhead. Learning continues indefinitely after deployment. We can then put an entire video in context as prompt! RoboTTT enables one-shot in-context learning from human video: in circuit board assembly, a human demonstrates a never-seen configuration once, and the robot imitates it faithfully. Humans drop things all the time, but we pick them up so fast that we don’t even notice. That reflex to fix is half of our physical competence. RoboTTT shows self-improvement on the fly: the robot is skilled at recovering from its own errors mid-episode, and each fix enters its context to inform the next move. The TTT core distills a general-purpose, failure-to-correction mapping from the training data. One more thing. What excites me the most is a new Context Scaling Curve: from 128 to 8K timesteps, closed-loop performance hill-climbs steadily with no sign of saturation. 8K-context pretraining beats 1K by 62%. What LLM enjoys, robotics should too. Soon, even 1M context is not a fantasy. Deep dive in thread:

We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 sec), instantly forgetting what just happened. We pushed to 3 orders of magnitude beyond SOTA. Introducing RoboTTT. Test-Time Training (“TTT”) carries a tiny model inside the model. Every incoming sensor reading triggers one gradient step on that tiny core, so the history keeps getting compressed into its weights. The hidden state has a fixed size (literally a small neural net), so the robot can “grok” arbitrarily long experience with little overhead. Learning continues indefinitely after deployment. We can then put an entire video in context as prompt! RoboTTT enables one-shot in-context learning from human video: in circuit board assembly, a human demonstrates a never-seen configuration once, and the robot imitates it faithfully. Humans drop things all the time, but we pick them up so fast that we don’t even notice. That reflex to fix is half of our physical competence. RoboTTT shows self-improvement on the fly: the robot is skilled at recovering from its own errors mid-episode, and each fix enters its context to inform the next move. The TTT core distills a general-purpose, failure-to-correction mapping from the training data. One more thing. What excites me the most is a new Context Scaling Curve: from 128 to 8K timesteps, closed-loop performance hill-climbs steadily with no sign of saturation. 8K-context pretraining beats 1K by 62%. What LLM enjoys, robotics should too. Soon, even 1M context is not a fantasy. Deep dive in thread:

Jim Fan

284,754 görüntüleme • 10 gün önce

Obsidian + method Karpathy + Claude Code = a quantum second brain that talks back. Most second brains are graveyards you clip 300 articles, tag 80 notes, build a graph that looks like a galaxy, then never open it again. Karpathy fix is stupid simple: 1 file, append only, new thought on top, review by scrolling no folders, no tags, no 40-minute “PKM setup” videos. The capture layer is 1 Obsidian vault with 1 file called stream md, where every idea, quote and link lands in under 10 seconds, because anything slower and you quit by day 4. Once a week Claude Code reads the whole vault from the terminal with 1 prompt “find the 5 ideas I keep circling without noticing” and sees patterns across 6 months you can’t hold in working memory. Instead of searching keywords you ask questions like “what did I think about agent pricing in March,” and Claude greps 4,000 notes and quotes your own words back with file paths. Then the vault becomes context drafting a post, a pitch or a spec, Claude pulls in your past thinking instead of generic internet mush, and your output starts sounding like you, compressed. The first week feels pointless at 20 notes, month 1 brings the first “wait, I already solved this” moment, by month 3 Claude connects 2 notes written 70 days apart and that connection becomes your best post of the year, by month 6 you stop asking Google things you already answered. The whole setup costs $0 in software and 1 evening. Notion sells you a workspace, Obsidian gives you files, Claude gives them a voice. Everyone rents a second brain this one lives on your disk and grows. You wrote the notes, and now something finally reads them.

Obsidian + method Karpathy + Claude Code = a quantum second brain that talks back. Most second brains are graveyards you clip 300 articles, tag 80 notes, build a graph that looks like a galaxy, then never open it again. Karpathy fix is stupid simple: 1 file, append only, new thought on top, review by scrolling no folders, no tags, no 40-minute “PKM setup” videos. The capture layer is 1 Obsidian vault with 1 file called stream md, where every idea, quote and link lands in under 10 seconds, because anything slower and you quit by day 4. Once a week Claude Code reads the whole vault from the terminal with 1 prompt “find the 5 ideas I keep circling without noticing” and sees patterns across 6 months you can’t hold in working memory. Instead of searching keywords you ask questions like “what did I think about agent pricing in March,” and Claude greps 4,000 notes and quotes your own words back with file paths. Then the vault becomes context drafting a post, a pitch or a spec, Claude pulls in your past thinking instead of generic internet mush, and your output starts sounding like you, compressed. The first week feels pointless at 20 notes, month 1 brings the first “wait, I already solved this” moment, by month 3 Claude connects 2 notes written 70 days apart and that connection becomes your best post of the year, by month 6 you stop asking Google things you already answered. The whole setup costs $0 in software and 1 evening. Notion sells you a workspace, Obsidian gives you files, Claude gives them a voice. Everyone rents a second brain this one lives on your disk and grows. You wrote the notes, and now something finally reads them.

West Lord

62,978 görüntüleme • 8 gün önce

Bradley Carnell comments on Cavan Sullivan’s clip of him being substituted over the weekend: “No, I have no problem with a guy who, you know, is frustrated to come off or not. No problem. I have no problem with any expectations that anyone has. But, you know, I’m not in an individual sport, I’m in a team sport. And I think anyone who knows the intensity we play at, we’ve done this for many, many months now. And, you know, I would think we shouldn’t make a mountain out of a molehill. This is something that is over and, in the heat of the moment, it didn’t affect anyone but Cavan. So this is something that he’s still learning as a young pro. And, you know, I think where his discipline and structure and work against the ball are concerned, you can see a lot of it now falling into place as it should be. But it doesn’t mean anyone’s automatic, right? Just because anyone carries a certain name on the back of their shoulders. I’ve never been that type of person, never been that type of coach, and never expected it as a player myself. So, you know, we all believe in the team, and the team is the most important thing.” #doop #MLS #usymnt #usmnt #MCFC 📹: Philadelphia Union and APPLE|MLS cc: American Ultras Talk | Marcus Chairez | US/SC | USMNTProspects

Bradley Carnell comments on Cavan Sullivan’s clip of him being substituted over the weekend: “No, I have no problem with a guy who, you know, is frustrated to come off or not. No problem. I have no problem with any expectations that anyone has. But, you know, I’m not in an individual sport, I’m in a team sport. And I think anyone who knows the intensity we play at, we’ve done this for many, many months now. And, you know, I would think we shouldn’t make a mountain out of a molehill. This is something that is over and, in the heat of the moment, it didn’t affect anyone but Cavan. So this is something that he’s still learning as a young pro. And, you know, I think where his discipline and structure and work against the ball are concerned, you can see a lot of it now falling into place as it should be. But it doesn’t mean anyone’s automatic, right? Just because anyone carries a certain name on the back of their shoulders. I’ve never been that type of person, never been that type of coach, and never expected it as a player myself. So, you know, we all believe in the team, and the team is the most important thing.” #doop #MLS #usymnt #usmnt #MCFC 📹: Philadelphia Union and APPLE|MLS cc: American Ultras Talk | Marcus Chairez | US/SC | USMNTProspects

José Roberto Nuñez

13,903 görüntüleme • 2 ay önce

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

GREG ISENBERG

193,095 görüntüleme • 3 ay önce

Your competitor spent 8 months and $50K building an AI voice agent SaaS. You typed one prompt on naïve and shipped the same thing today. That is not an exaggeration. That is exactly what just happened. 🔗 I opened Naive, typed one sentence, and watched a full team of AI employees spin up and start building my AI voice agent SaaS platform from scratch. No dev agency. No co-founder. No seed round. No 8-month runway burn. Here's what my team built, and is running right now: 🔧 Engineer: architected the entire platform, wrote production code, shipped without a single review from me. 📞 Sales rep: started booking demos with potential customers before the platform was even fully live. 🎧 Support agent: set up the entire ticket system and started handling user queries from day one. 💰 Finance manager: set up revenue tracking, reconciled accounts, and started generating reports automatically. Each one has their own email inbox, bank account, phone number, and workspace. They share context. They delegate tasks to each other. They get sharper with every user onboarded and every bug resolved. My entire prompt: "Build me an AI voice agent SaaS platform." That's all I typed. Then I walked away. No technical background. No dev experience. No agency retainer required. What founders on this platform are seeing right now: → Real ARR with zero human employees → +32% revenue growth week over week → +42% tasks completed week over week You have a SaaS idea sitting in your head right now. One prompt on naïve and it's already shipping. Your competitor burned 8 months to get where you'll be in 10 minutes. 👉 #NaïveAI2B9YHR

Your competitor spent 8 months and $50K building an AI voice agent SaaS. You typed one prompt on naïve and shipped the same thing today. That is not an exaggeration. That is exactly what just happened. 🔗 I opened Naive, typed one sentence, and watched a full team of AI employees spin up and start building my AI voice agent SaaS platform from scratch. No dev agency. No co-founder. No seed round. No 8-month runway burn. Here's what my team built, and is running right now: 🔧 Engineer: architected the entire platform, wrote production code, shipped without a single review from me. 📞 Sales rep: started booking demos with potential customers before the platform was even fully live. 🎧 Support agent: set up the entire ticket system and started handling user queries from day one. 💰 Finance manager: set up revenue tracking, reconciled accounts, and started generating reports automatically. Each one has their own email inbox, bank account, phone number, and workspace. They share context. They delegate tasks to each other. They get sharper with every user onboarded and every bug resolved. My entire prompt: "Build me an AI voice agent SaaS platform." That's all I typed. Then I walked away. No technical background. No dev experience. No agency retainer required. What founders on this platform are seeing right now: → Real ARR with zero human employees → +32% revenue growth week over week → +42% tasks completed week over week You have a SaaS idea sitting in your head right now. One prompt on naïve and it's already shipping. Your competitor burned 8 months to get where you'll be in 10 minutes. 👉 #NaïveAI2B9YHR

Gina Acosta

15,888 görüntüleme • 2 ay önce

lee from cursor JUST showed me the future of coding in this 29 min tutorial. what if instead of thinking about coding as you sitting alone in front of a screen , you started to think about it as you and a swarm of agents each taking on very specific roles, each showing up exactly when you need them, each running in the background without ever needing a coffee break. imagine a bugbot that doesn’t just review your pull request but triages the issue instantly, leaves intelligent comments, and in some cases even proposes a fix before a teammate has had the chance to read the description. imagine a security agent that quietly scans your code for vulnerabilities and flags them long before they become liabilities. imagine an agent dedicated to software culture, enforcing the little rules your team has decided matter, whether that’s never skipping loading states, banning certain lazy marketing phrases in your code comments, or making sure tests are always included. lee walked me through how all of this already exists inside cursor. he spun up custom commands like /code-review or /security-review that behave less like toys and more like trusted coworkers who have internalized the way your team thinks about quality. and when he combined that with rails, type safety, linters, formatting rules, test suites.... the agents learned to check themselves against the rails and fix mistakes automatically. you end up with a system where the codebase begins to feel alive, constantly watching itself, constantly healing. another thing i learned from lee was watching how he doesn’t pile everything into one giant context and hope for magic. he creates new chats for every new task, sometimes twenty or more in a single day, each one a fresh brain that isn’t bogged down by yesterday’s details. it’s a discipline that keeps the agents sharp and the outputs clean. pro tip, thanks Lee Robinson. this was a cool glimpse into the future of coding and some tips on how to squeeze the most out of cursor. anything is possible.

lee from cursor JUST showed me the future of coding in this 29 min tutorial. what if instead of thinking about coding as you sitting alone in front of a screen , you started to think about it as you and a swarm of agents each taking on very specific roles, each showing up exactly when you need them, each running in the background without ever needing a coffee break. imagine a bugbot that doesn’t just review your pull request but triages the issue instantly, leaves intelligent comments, and in some cases even proposes a fix before a teammate has had the chance to read the description. imagine a security agent that quietly scans your code for vulnerabilities and flags them long before they become liabilities. imagine an agent dedicated to software culture, enforcing the little rules your team has decided matter, whether that’s never skipping loading states, banning certain lazy marketing phrases in your code comments, or making sure tests are always included. lee walked me through how all of this already exists inside cursor. he spun up custom commands like /code-review or /security-review that behave less like toys and more like trusted coworkers who have internalized the way your team thinks about quality. and when he combined that with rails, type safety, linters, formatting rules, test suites.... the agents learned to check themselves against the rails and fix mistakes automatically. you end up with a system where the codebase begins to feel alive, constantly watching itself, constantly healing. another thing i learned from lee was watching how he doesn’t pile everything into one giant context and hope for magic. he creates new chats for every new task, sometimes twenty or more in a single day, each one a fresh brain that isn’t bogged down by yesterday’s details. it’s a discipline that keeps the agents sharp and the outputs clean. pro tip, thanks Lee Robinson. this was a cool glimpse into the future of coding and some tips on how to squeeze the most out of cursor. anything is possible.

GREG ISENBERG

47,160 görüntüleme • 10 ay önce

I just built an AI-powered creative search engine with Gemini Embedding 2 + Claude Code 🤯 Drop in your UGC clips, product shots, and ad variations — then search through everything in plain English. "Show me all the unboxing clips." "Find product shots with natural lighting." "Which creator talked about sensitive skin?" All inside Claude Code. Perfect for DTC brands and agencies sitting on hundreds of creative files they can never find when they actually need them. If you're digging through a folder of random file names, scrubbing through raw footage to find that one clip, and relying on memory to track down what's already been shot... This system eliminates the entire loop: → Drop your videos, images, and docs into a project folder → One prompt to Claude Code — it builds the entire search app for you → Google's new Gemini Embedding 2 model actually watches your videos and looks at your images → It understands what's inside each file — not just the file name → Search in plain English and get back the actual assets with confidence scores No scrolling through folders. No relying on file names to find anything. No re-shooting footage you already have. What you get: → A searchable library of every creative asset your brand has ever produced → Natural language search across video, images, and documents at the same time → Results that show the actual files inline — play videos, view images, read docs → A system that gets smarter every time you add richer descriptions to your assets One free API key. No monthly subscriptions. Runs on your machine. I put together a full playbook with the exact build prompt, the setup process, and DTC/agency use cases to get this running in under 30 minutes. Want the full playbook? > Like this post > Comment "SEARCH" And I'll send it over (must be following so I can DM)

Mike Futia

12,260 görüntüleme • 4 ay önce

💥BANG! Surgeon who worked at the hospital that supposedly got the first Covid patient in the U.S.— "IT WAS ALL A PROPAGANDA OP" "Everything in the news was wrong. IT WAS ALL A LIE" The "lab leak" isn't the real Covid story. The real Covid story is THERE WAS NO PANDEMIC. This lightly edited clip of Dr. James Miller (james miller), a trauma surgeon who worked at the WA hospital that—supposedly—got the first "covid" case in the U.S., is taken from a conversation with Alix Mayer (Alix Mayer) posted to YouTube on July 8, 2026. ---------------Pulled quotes from the clip---------------- "First of all, everything in the news was wrong. It was all a lie" "So our hospital had the first diagnosed Covid case in America. It was a guy who came back from China. Allegedly. It was all a propaganda op" "the first diagnosed Covid case, who came from Wuhan, China... showed up—allegedly—[at] our hospital doors. But here's the part that's weird. So the reason the hospital has such a cumbersome name of Providence Regional Medical Center, Everett, is because it's actually two campuses. And the second campus is just a birthing center and a rehab unit. So allegedly, they housed that guy there" "at least at that campus. Now, the CMO told me, Oh, that's where we have our special negative-pressure rooms. Which was a bald-faced lie, because every ICU bed was a negative-pressure room. And so that's just silly" "Additionally, as a trauma surgeon, because you deal with all the bad cases, particularly in the middle of the night. Everyone tells you everything. I spoke to zero nurses, zero infectious disease doctors that ever took care of that patient" "So maybe allegedly, one of the infectious disease doctors, who I never met or never talked to about it, kept his mouth shut, treated this guy, but I never heard about it. So none of the pulmonologists, the lung specialist, knew about him. No one talked. So the whole thing was silly" "why would you admit a guy to a hospital campus that has no ICU when you're worried about a deadly pandemic? It's just illogical. So just from that, it was ridiculous" "I'll just absolutely hold out. There's a theoretical chance this actually happened. It just never happened with any other infectious disease. Every tuberculosis patient came to the ICU because there were negative pressure rooms. Every other infectious disease we're worried about came to the ICU so that. It's just not logical... [and] I just knew everybody, and no one met the guy"

💥BANG! Surgeon who worked at the hospital that supposedly got the first Covid patient in the U.S.— "IT WAS ALL A PROPAGANDA OP" "Everything in the news was wrong. IT WAS ALL A LIE" The "lab leak" isn't the real Covid story. The real Covid story is THERE WAS NO PANDEMIC. This lightly edited clip of Dr. James Miller (james miller), a trauma surgeon who worked at the WA hospital that—supposedly—got the first "covid" case in the U.S., is taken from a conversation with Alix Mayer (Alix Mayer) posted to YouTube on July 8, 2026. ---------------Pulled quotes from the clip---------------- "First of all, everything in the news was wrong. It was all a lie" "So our hospital had the first diagnosed Covid case in America. It was a guy who came back from China. Allegedly. It was all a propaganda op" "the first diagnosed Covid case, who came from Wuhan, China... showed up—allegedly—[at] our hospital doors. But here's the part that's weird. So the reason the hospital has such a cumbersome name of Providence Regional Medical Center, Everett, is because it's actually two campuses. And the second campus is just a birthing center and a rehab unit. So allegedly, they housed that guy there" "at least at that campus. Now, the CMO told me, Oh, that's where we have our special negative-pressure rooms. Which was a bald-faced lie, because every ICU bed was a negative-pressure room. And so that's just silly" "Additionally, as a trauma surgeon, because you deal with all the bad cases, particularly in the middle of the night. Everyone tells you everything. I spoke to zero nurses, zero infectious disease doctors that ever took care of that patient" "So maybe allegedly, one of the infectious disease doctors, who I never met or never talked to about it, kept his mouth shut, treated this guy, but I never heard about it. So none of the pulmonologists, the lung specialist, knew about him. No one talked. So the whole thing was silly" "why would you admit a guy to a hospital campus that has no ICU when you're worried about a deadly pandemic? It's just illogical. So just from that, it was ridiculous" "I'll just absolutely hold out. There's a theoretical chance this actually happened. It just never happened with any other infectious disease. Every tuberculosis patient came to the ICU because there were negative pressure rooms. Every other infectious disease we're worried about came to the ICU so that. It's just not logical... [and] I just knew everybody, and no one met the guy"

Sense Receptor

46,653 görüntüleme • 13 gün önce

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

GREG ISENBERG

375,365 görüntüleme • 4 ay önce

I'm making over $1,000 an hour with one AI offer. The entire thing runs on Claude Opus 4.8. I call it the AI Concierge. Clients pay me $1,500+ a month for two 45-minute calls where we build their AI systems live, on their screen. I have 4 clients. I'm capping at 6. Here's the entire model: 1) The intake form is the audit. A 10-minute JotForm (built by Claude) surfaces their time sinks and hands me 1-3 AI opportunities before call one. 2) Done-with-you, not done-for-you. They share their screen. We build skills, set up Cowork, and write context files together. They learn to drive. (Done-for-you is the upsell.) 3) Every session runs through AOA: Audit, Optimize, Automate. Fix the process first, then turn it into a skill. Automating chaos just gives you faster chaos. 4) Day one has to move the needle. We ship at least one skill or automation on call one. No first-call win, dead engagement. 5) Unlimited Voxer between calls. They send a voice message, I reply in under 12 business hours. A 24/7 partner, not a guy they see twice a month. 6) The Notion hub is the renewal mechanism. Every call logs a quantified list of what we built. "Call one: 2 skills, 3 context files, Cowork live" makes $1.5K a month a no-brainer. 7) I never fill Notion out by hand. Two Claude skills log the call, pull the action items, and draft the recap email. 30 seconds. 8) Pricing ladder: $1,000/month, then $1,500 at 2 clients, then $1,800. At $1,500 you're already at $1,000/hour. If everyone says yes then you're priced too low. Two things that make this work: 1) Build the fulfillment infrastructure once. An afternoon. Then it runs itself outside the calls. 2) The value must be visible. People renew what they can measure. Full breakdown below. Go watch.

I'm making over $1,000 an hour with one AI offer. The entire thing runs on Claude Opus 4.8. I call it the AI Concierge. Clients pay me $1,500+ a month for two 45-minute calls where we build their AI systems live, on their screen. I have 4 clients. I'm capping at 6. Here's the entire model: 1) The intake form is the audit. A 10-minute JotForm (built by Claude) surfaces their time sinks and hands me 1-3 AI opportunities before call one. 2) Done-with-you, not done-for-you. They share their screen. We build skills, set up Cowork, and write context files together. They learn to drive. (Done-for-you is the upsell.) 3) Every session runs through AOA: Audit, Optimize, Automate. Fix the process first, then turn it into a skill. Automating chaos just gives you faster chaos. 4) Day one has to move the needle. We ship at least one skill or automation on call one. No first-call win, dead engagement. 5) Unlimited Voxer between calls. They send a voice message, I reply in under 12 business hours. A 24/7 partner, not a guy they see twice a month. 6) The Notion hub is the renewal mechanism. Every call logs a quantified list of what we built. "Call one: 2 skills, 3 context files, Cowork live" makes $1.5K a month a no-brainer. 7) I never fill Notion out by hand. Two Claude skills log the call, pull the action items, and draft the recap email. 30 seconds. 8) Pricing ladder: $1,000/month, then $1,500 at 2 clients, then $1,800. At $1,500 you're already at $1,000/hour. If everyone says yes then you're priced too low. Two things that make this work: 1) Build the fulfillment infrastructure once. An afternoon. Then it runs itself outside the calls. 2) The value must be visible. People renew what they can measure. Full breakdown below. Go watch.

Corey Ganim

103,805 görüntüleme • 1 ay önce

Shamim Akhter, a professor at Aliah University #Kolkata, did everything the system asked of him. Born and listed in the 2003 Bihar voter rolls. His parents are there in 2003 list and also in 2025 Bihar list. He moved to Kolkata in 2016. Updated his voter ID. Voted in 2019, 2021, 2024. And then he was gone. Post SIR, his name has been deleted from the #Bengal voter list. No warning. No clear reason. Just DELETED. But this is not just about one name. Inside his home, met his wife, bedridden - dependent on an oxygen cylinder for every breath. A family already battling survival is now forced to confront something far more invisible - uncertainty. Akhter broke down, not over politics, but over fear. Fear of systems turning him unrecognisable. Fear of being questioned. Fear of not being seen. “What if I lose my job because i lost my right to vote - how will I take of my wife’s medical expenses” he asked. And then, the blow that makes it harder to ignore - his son, an MBBS student with a birth certificate, has also been deleted. Three lives. One silent fear. The wife is still on the voter list. She is the one who can barely move. And yet, she now says she will go and vote. Under any circumstances. Because her husband and son have been erased, thus she is preparing to show up - not just to vote, but to register their pain before a system that has Deleted their peace A voter ID is not just a document - it is the most basic acknowledgment: you belong. When that disappears, what replaces it is not just inconvenience - it is doubt. #BengalElection2026

Shamim Akhter, a professor at Aliah University #Kolkata, did everything the system asked of him. Born and listed in the 2003 Bihar voter rolls. His parents are there in 2003 list and also in 2025 Bihar list. He moved to Kolkata in 2016. Updated his voter ID. Voted in 2019, 2021, 2024. And then he was gone. Post SIR, his name has been deleted from the #Bengal voter list. No warning. No clear reason. Just DELETED. But this is not just about one name. Inside his home, met his wife, bedridden - dependent on an oxygen cylinder for every breath. A family already battling survival is now forced to confront something far more invisible - uncertainty. Akhter broke down, not over politics, but over fear. Fear of systems turning him unrecognisable. Fear of being questioned. Fear of not being seen. “What if I lose my job because i lost my right to vote - how will I take of my wife’s medical expenses” he asked. And then, the blow that makes it harder to ignore - his son, an MBBS student with a birth certificate, has also been deleted. Three lives. One silent fear. The wife is still on the voter list. She is the one who can barely move. And yet, she now says she will go and vote. Under any circumstances. Because her husband and son have been erased, thus she is preparing to show up - not just to vote, but to register their pain before a system that has Deleted their peace A voter ID is not just a document - it is the most basic acknowledgment: you belong. When that disappears, what replaces it is not just inconvenience - it is doubt. #BengalElection2026

Tamal Saha

94,229 görüntüleme • 2 ay önce

𝐈 𝐫𝐞𝐜𝐞𝐧𝐭𝐥𝐲 𝐦𝐨𝐯𝐞𝐝 𝐢𝐧𝐭𝐨 𝐦𝐲 𝐧𝐞𝐰 𝐌𝐚𝐧𝐬𝐢𝐨𝐧. Something that once felt far away, almost unrealistic at some point. This is not just a win, but a reminder of what consistent effort can actually turn into. few years ago I didn’t have a clear direction. I just knew I wanted more. More than where I was, more than what I was seeing, more than what felt possible at the time. So I started trying things. Failing quietly, learning, starting again. No big announcements, no validation, just me showing up every day and figuring it out as I went. At first my only goal was simple. Just get better, earn something, prove to myself that I could actually make this work. And I did. But like most people, there were moments where it started to feel like that was enough, like I could slow down a bit. That mindset is dangerous. Because the moment you tell yourself this is okay, you stop pushing. And when you stop pushing, you stop growing. I had to change that. I shifted my focus. I stopped just trying to get by and started building something real. I leaned into Web3, started putting myself out there, connecting with people and creating opportunities instead of waiting for them. And that changed everything. It made me realize something. A lot of people don’t lack motivation. They’ve just outgrown their reason. When your goals are too small, your effort becomes small. When your vision expands, your actions follow. Right now I’m not where I want to be yet, but I’m far from where I started and that gap means everything to me. So I’m raising the standard again. Bigger goals, more visibility, building things that actually matter and not getting comfortable too early. If you’ve been part of my journey in any way, I appreciate you. If your direction feels small, it’s probably time to expand it. The bigger the life you want, the bigger the standard you need. Web3 did this, God did this, see you at the top 💙🦅

𝐈 𝐫𝐞𝐜𝐞𝐧𝐭𝐥𝐲 𝐦𝐨𝐯𝐞𝐝 𝐢𝐧𝐭𝐨 𝐦𝐲 𝐧𝐞𝐰 𝐌𝐚𝐧𝐬𝐢𝐨𝐧. Something that once felt far away, almost unrealistic at some point. This is not just a win, but a reminder of what consistent effort can actually turn into. few years ago I didn’t have a clear direction. I just knew I wanted more. More than where I was, more than what I was seeing, more than what felt possible at the time. So I started trying things. Failing quietly, learning, starting again. No big announcements, no validation, just me showing up every day and figuring it out as I went. At first my only goal was simple. Just get better, earn something, prove to myself that I could actually make this work. And I did. But like most people, there were moments where it started to feel like that was enough, like I could slow down a bit. That mindset is dangerous. Because the moment you tell yourself this is okay, you stop pushing. And when you stop pushing, you stop growing. I had to change that. I shifted my focus. I stopped just trying to get by and started building something real. I leaned into Web3, started putting myself out there, connecting with people and creating opportunities instead of waiting for them. And that changed everything. It made me realize something. A lot of people don’t lack motivation. They’ve just outgrown their reason. When your goals are too small, your effort becomes small. When your vision expands, your actions follow. Right now I’m not where I want to be yet, but I’m far from where I started and that gap means everything to me. So I’m raising the standard again. Bigger goals, more visibility, building things that actually matter and not getting comfortable too early. If you’ve been part of my journey in any way, I appreciate you. If your direction feels small, it’s probably time to expand it. The bigger the life you want, the bigger the standard you need. Web3 did this, God did this, see you at the top 💙🦅

CryptoMaMa

407,757 görüntüleme • 3 ay önce

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

419,636 görüntüleme • 7 ay önce