正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

What does "trust remote code" actually approve? In most local AI tools, the answer is: that repo, indefinitely. That matters more now. In May, HiddenLayer reported a trending Hugging Face repo whose loader. py downloaded an infostealer on Windows. JFrog counted 495 malicious models that month. I spent some... time with Unsloth Studio's approach. It handles it differently. Approval is tied to a fingerprint of the scanned code. Change the code, and you're asked again. Critical findings can't be approved. Code it can't scan is blocked. There's no trusted-org bypass. Weights are checked on their own. Studio reads Hugging Face's malware verdict without unpickling the file. Flagged files in the loading path are blocked, including weight shards. .bin weights load with weights_only=True on PyTorch 2.6+. The supply chain gets attention too. PyPI and npm packages are content-scanned. npm packages need to be at least 7 days old. GitHub Actions are pinned, and llama.cpp binaries are checksum-verified. Trivy isn't installed at all, after a compromised Trivy exposed LiteLLM's publishing credentials in March. Accounts are covered as well. Passwords use PBKDF2-HMAC-SHA256, failed logins are rate-limited, and the first admin password is random. Managed accounts can't run repository code. For remote access, --secure serves HTTPS through a Cloudflared tunnel. --disable-tools is recommended when exposing Studio. What it doesn't do: sandbox approved model code. Server-side tools still run as your OS user. Local folders aren't covered by the file check, and a pending scan status doesn't block. That's a reasonable line to draw, as long as you know where it is. Read our full analysis on this: Here is the Unsloth's docs: Unsloth AI Unslothshow more

Marktechpost AI

11,789 subscribers

534,474 次观看 • 4 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

Akshay 🚀

30,876 次观看 • 1 年前

Sriram Krishnan reveals why it's easier to defend American code with a Chinese model than an American one right now: "I don't think it is great that the leading open weight models or open source models are not American. There's some great innovation happening with Moonshot and with DeepSeek and with Qwen, but I would much rather prefer that the leading models are American." "Linus Torvalds of Linux fame had a law that given enough eyes, all bugs are shallow. Open weight models are inherently secure because when you download a model off Hugging Face, the entire world can take it apart, inspect it, fine-tune it, look at it in ways that you absolutely cannot if they are closed." "There was an incident with Hugging Face that got reported on earlier today. Hugging Face seems to have found that somebody was using an AI LLM agent to hammer them at multiple places and to find ways to break in." "The way to counter that is to make sure American or Western or allies defenders have access to the best models to make our software just more secure." "It may be harder to look at your own code for exploits with Fable than it is when you use a Chinese model. That's just like a weird spot to be, and I think we should fix that." Sriram Krishnan

Sriram Krishnan reveals why it's easier to defend American code with a Chinese model than an American one right now: "I don't think it is great that the leading open weight models or open source models are not American. There's some great innovation happening with Moonshot and with DeepSeek and with Qwen, but I would much rather prefer that the leading models are American." "Linus Torvalds of Linux fame had a law that given enough eyes, all bugs are shallow. Open weight models are inherently secure because when you download a model off Hugging Face, the entire world can take it apart, inspect it, fine-tune it, look at it in ways that you absolutely cannot if they are closed." "There was an incident with Hugging Face that got reported on earlier today. Hugging Face seems to have found that somebody was using an AI LLM agent to hammer them at multiple places and to find ways to break in." "The way to counter that is to make sure American or Western or allies defenders have access to the best models to make our software just more secure." "It may be harder to look at your own code for exploits with Fable than it is when you use a Chinese model. That's just like a weird spot to be, and I think we should fix that." Sriram Krishnan

MTS

61,234 次观看 • 2 个月前

Everyone is a VC. Bgauc16XYRw6c56QVTbbaTD7yq8L6zXyYGyjV2U3BAGS Today we are announcing the first on-chain VC where trenchers become capital partners. Here's how it works: > Join via access code, invite others in → Back devs BEFORE tokenization > All developers are vetted and verified; code is verified on Github. > Devs get real resources for token success including builder credits, marketing tools, Dex tools and more. > Communities get structured access to projects that actually want to support them No more blind launches. Devs are onboarded and aligned with their community from day one. This is just the beginning. A lot more features are coming to bring real legitimacy to this industry — and we're excited to be the first ones doing it. Starter Access Codes for Special Powers :) : 8410C045 3C87B633 22EA9A74 703265E4 _______ Over the past 6 months we've turned into a development studio on BAGS - supporting numerous developers with our own funding. Today we turn that power over to you and invite you to become partners too. 5% of $INVISIBLE is locked forever as liquidity 5% of $INVISIBLE supply is burned More soon.

Everyone is a VC. Bgauc16XYRw6c56QVTbbaTD7yq8L6zXyYGyjV2U3BAGS Today we are announcing the first on-chain VC where trenchers become capital partners. Here's how it works: > Join via access code, invite others in → Back devs BEFORE tokenization > All developers are vetted and verified; code is verified on Github. > Devs get real resources for token success including builder credits, marketing tools, Dex tools and more. > Communities get structured access to projects that actually want to support them No more blind launches. Devs are onboarded and aligned with their community from day one. This is just the beginning. A lot more features are coming to bring real legitimacy to this industry — and we're excited to be the first ones doing it. Starter Access Codes for Special Powers :) : 8410C045 3C87B633 22EA9A74 703265E4 _______ Over the past 6 months we've turned into a development studio on BAGS - supporting numerous developers with our own funding. Today we turn that power over to you and invite you to become partners too. 5% of $INVISIBLE is locked forever as liquidity 5% of $INVISIBLE supply is burned More soon.

invisible

27,978 次观看 • 7 个月前

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Malte Ubl

125,326 次观看 • 9 个月前

$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

56,559 次观看 • 4 个月前

A Robinhood Chain receipt machine that remembers what the changelog forgets. It's called RUMZO. Most tools show you a builder token's chart. RUMZO shows you its commits and its contract at the same moment, then saves the proof so the story can't be rewritten later. [give it a token address and a public GitHub repo] → Pulls source, tests, docs and manifests at one pinned commit. → Reads launch stage, fees, buyback and locker flags at one pinned block. → Saves both sides as a receipt with commit, block number and observation time. → Run it again later and it diffs the two receipts. If a dev says the tests are done, the fees changed or the locker is on, RUMZO does not read the announcement and guess. It already has the receipt from last time. Which source files changed, whether tests and docs moved with them, which contract settings flipped in between - all of it side by side. Missing data stays marked unknown, nothing gets filled in. Local web UI, a CLI, JSON and Markdown exports. And the whole thing is intentionally READ ONLY. No wallet. No signer. No repo code executed. No buy button. Small raccoon. Lots of receipts. Open source, repo in the first reply ↓

A Robinhood Chain receipt machine that remembers what the changelog forgets. It's called RUMZO. Most tools show you a builder token's chart. RUMZO shows you its commits and its contract at the same moment, then saves the proof so the story can't be rewritten later. [give it a token address and a public GitHub repo] → Pulls source, tests, docs and manifests at one pinned commit. → Reads launch stage, fees, buyback and locker flags at one pinned block. → Saves both sides as a receipt with commit, block number and observation time. → Run it again later and it diffs the two receipts. If a dev says the tests are done, the fees changed or the locker is on, RUMZO does not read the announcement and guess. It already has the receipt from last time. Which source files changed, whether tests and docs moved with them, which contract settings flipped in between - all of it side by side. Missing data stays marked unknown, nothing gets filled in. Local web UI, a CLI, JSON and Markdown exports. And the whole thing is intentionally READ ONLY. No wallet. No signer. No repo code executed. No buy button. Small raccoon. Lots of receipts. Open source, repo in the first reply ↓

Nekt0

57,088 次观看 • 1 个月前

Nobody is writing 90% of their code using AI. Here's the uncomfortable truth: The real productivity gain from using AI to write code is closer to 10%, nowhere near the 90% people claim. Sundar Pichai said in 2024 that 30% of the new code at Google was AI-generated. However, he went on to admit, during Lex Friedman's podcast, that engineering velocity had only increased by about 10%. AI-generated code isn't free code. It still has to be reviewed, tested, and made production-ready. Optimizing a single step (code generation) doesn't boost output if bottlenecks shift elsewhere (code reviews). It doesn't matter how much code you generate if you can't keep up the review process. The solution: Automate as much as you can the review and verification of your code. I'm working with Sonar, who is sponsoring this post, and they will take care of the code quality and security analysis of your code: • They review over 300B lines of code every single day • They cover reliability, security, and maintainability for your code • You can integrate them into your CI/CD pipeline • You can install them in your IDE (I use their VSCode extension) • Support for more than 30 languages Here is a link so you can check them out:

Nobody is writing 90% of their code using AI. Here's the uncomfortable truth: The real productivity gain from using AI to write code is closer to 10%, nowhere near the 90% people claim. Sundar Pichai said in 2024 that 30% of the new code at Google was AI-generated. However, he went on to admit, during Lex Friedman's podcast, that engineering velocity had only increased by about 10%. AI-generated code isn't free code. It still has to be reviewed, tested, and made production-ready. Optimizing a single step (code generation) doesn't boost output if bottlenecks shift elsewhere (code reviews). It doesn't matter how much code you generate if you can't keep up the review process. The solution: Automate as much as you can the review and verification of your code. I'm working with Sonar, who is sponsoring this post, and they will take care of the code quality and security analysis of your code: • They review over 300B lines of code every single day • They cover reliability, security, and maintainability for your code • You can integrate them into your CI/CD pipeline • You can install them in your IDE (I use their VSCode extension) • Support for more than 30 languages Here is a link so you can check them out:

Santiago

296,750 次观看 • 1 年前

THE HEAD ENGINEER AT ANTHROPIC LEAKED THE PATH FROM ZERO TO AN ENGINEER ON $1.4M A YEAR WITH A FULLY AUTOMATED TEAM in 12 days you reach the point where your job is deciding - one file carries the rest, and that's $120K a month. chat → terminal → skills → patterns → gates → fleet while you're copying answers into the editor, you are the wire between the model and the code - all 4 hops are yours. in the terminal copy-paste ends for good - the model sees the whole repo and git, not the snippet you pasted. skills is the last point where you're still tuning wording - 7 procedures sit on disk, exactly 1 enters the window. after that runs the real border: before it you improve prompts, past it you build something that doesn't depend on them. quality stops being how you phrased it - it becomes a contract and an evaluator that never gets tired. gates replace review: the cheap model triages the findings, the expensive one decides on the real ones - rejection happens before you open anything. a gate that never rejects anything is a status badge, not a gate. at the end it's 8 workers, cron and a file that edits itself - you read the morning report and you started nothing. skip a link and nothing throws an error, the reports keep arriving - they just stop being true. save this and paste it into Claude Code - one file, 12 days, zero ways to jump a step ↓

THE HEAD ENGINEER AT ANTHROPIC LEAKED THE PATH FROM ZERO TO AN ENGINEER ON $1.4M A YEAR WITH A FULLY AUTOMATED TEAM in 12 days you reach the point where your job is deciding - one file carries the rest, and that's $120K a month. chat → terminal → skills → patterns → gates → fleet while you're copying answers into the editor, you are the wire between the model and the code - all 4 hops are yours. in the terminal copy-paste ends for good - the model sees the whole repo and git, not the snippet you pasted. skills is the last point where you're still tuning wording - 7 procedures sit on disk, exactly 1 enters the window. after that runs the real border: before it you improve prompts, past it you build something that doesn't depend on them. quality stops being how you phrased it - it becomes a contract and an evaluator that never gets tired. gates replace review: the cheap model triages the findings, the expensive one decides on the real ones - rejection happens before you open anything. a gate that never rejects anything is a status badge, not a gate. at the end it's 8 workers, cron and a file that edits itself - you read the morning report and you started nothing. skip a link and nothing throws an error, the reports keep arriving - they just stop being true. save this and paste it into Claude Code - one file, 12 days, zero ways to jump a step ↓

Sprytix

10,836 次观看 • 1 个月前

Suno is limiting downloads, basically making a lot of the songs you make locked in their 'walled garden'. One of their main competitors, Udio, did the same thing after a settlement with UMG that restricts any downloads. This is 100% an injunction from the music labels who want to limit the "damage" that AI does to the profitability of music. There are two viable alternatives... >Minimax music 3.0. It is currently free to use up to 500 songs a day as long as your account qualifies for beta testing their music model, which should be anyone. It is a closed-weight model, but there are no restrictions on what you download and how much you download. The music quality is not as good as Udio or Suno, but it's pretty close overall, and it can understand very complex prompts to guide music generation. >Open-source music is not a very good alternative... but right now SongGeneration-LeVo2 is the best AI music model that's open-source right now. The music I put on the post is one such generation that I created on my PC. The problem is that it's hard to use. The comfyUI version requires installation on a separate portable install, specific transformer and flash attention versions, and additional libraries installed. The required models and checkpoints are scattered around Hugging Face, and some of the links from the original repo are dead. There are not many English guides, and most of the training data is in Chinese, so it struggles with English lyrics. To some extent, the demand for music generation isn't that high, compared to images and videos, so overall not many alternatives are around.

Suno is limiting downloads, basically making a lot of the songs you make locked in their 'walled garden'. One of their main competitors, Udio, did the same thing after a settlement with UMG that restricts any downloads. This is 100% an injunction from the music labels who want to limit the "damage" that AI does to the profitability of music. There are two viable alternatives... >Minimax music 3.0. It is currently free to use up to 500 songs a day as long as your account qualifies for beta testing their music model, which should be anyone. It is a closed-weight model, but there are no restrictions on what you download and how much you download. The music quality is not as good as Udio or Suno, but it's pretty close overall, and it can understand very complex prompts to guide music generation. >Open-source music is not a very good alternative... but right now SongGeneration-LeVo2 is the best AI music model that's open-source right now. The music I put on the post is one such generation that I created on my PC. The problem is that it's hard to use. The comfyUI version requires installation on a separate portable install, specific transformer and flash attention versions, and additional libraries installed. The required models and checkpoints are scattered around Hugging Face, and some of the links from the original repo are dead. There are not many English guides, and most of the training data is in Chinese, so it struggles with English lyrics. To some extent, the demand for music generation isn't that high, compared to images and videos, so overall not many alternatives are around.

Emerald Apple

20,420 次观看 • 2 个月前

Y Combinator CEO, Garry Tan, took the stage for 42 minutes at Startup School 2026 and explained how to build your own personal AGI better than any paid AI course. This is what he told the room: 1. The leverage is in your context, not the model. Tan watches hundreds of founders use identical models every batch. "There are 2x people and there are 100x people who are using the same Claude. Same weights, same context window size, same API. But the leverage is not in the weights." The gap between users is now bigger than the gap between models. 2. One person's output went up 400x. In 2013 Tan shipped maybe 14 useful lines of code a day as a YC partner, dead on the median for programmer productivity. "I did the math on my output, and I'm at about 400x what I did in 2013." 3. Agents run on a different working memory. Humans hold 7 things in their head at once. Every org chart and checklist ever built is a patch for that limit. "An AI agent holds a million tokens. That's about a thousand pages. Three Harry Potter books sitting open on its head all at once." You're still running your week on tools built for the 7-digit brain. 4. Markdown is code now. Tan's stack is mostly skill files: pages of plain English an agent can execute. "If you can write clear instructions in English, you're a programmer. The compiler is a language model." At YC, finance and events staff who never opened a terminal are building automations. 5. Your history is your moat. Tan's agent runs on a personal wiki: about 220,000 markdown pages covering 25 years of email, meetings, notes and decisions. "When my agent does anything, it does knowing everything I know. And that's the difference between an assistant and a colleague." No frontier model has your context. That's the one asset nobody can replicate. 6. Never do one-off work. Most people run a task with an agent, close the window and throw the learning away. Tan ends every task by having the agent turn what it did into a reusable skill file. "If you have to ask for something twice, you failed." Captured skills compound daily. Amnesia resets you to zero every morning. 7. Own your skill files before your employer does. A skill file is your judgment, extracted and executable. The only question is who controls it. "Own your skills because if you don't, your job becomes a skill file." Files in your repo compound your career. Files in the company's repo run your judgment without you. Watch it, then read the step-by-step guide on becoming an AI engineer.

Y Combinator CEO, Garry Tan, took the stage for 42 minutes at Startup School 2026 and explained how to build your own personal AGI better than any paid AI course. This is what he told the room: 1. The leverage is in your context, not the model. Tan watches hundreds of founders use identical models every batch. "There are 2x people and there are 100x people who are using the same Claude. Same weights, same context window size, same API. But the leverage is not in the weights." The gap between users is now bigger than the gap between models. 2. One person's output went up 400x. In 2013 Tan shipped maybe 14 useful lines of code a day as a YC partner, dead on the median for programmer productivity. "I did the math on my output, and I'm at about 400x what I did in 2013." 3. Agents run on a different working memory. Humans hold 7 things in their head at once. Every org chart and checklist ever built is a patch for that limit. "An AI agent holds a million tokens. That's about a thousand pages. Three Harry Potter books sitting open on its head all at once." You're still running your week on tools built for the 7-digit brain. 4. Markdown is code now. Tan's stack is mostly skill files: pages of plain English an agent can execute. "If you can write clear instructions in English, you're a programmer. The compiler is a language model." At YC, finance and events staff who never opened a terminal are building automations. 5. Your history is your moat. Tan's agent runs on a personal wiki: about 220,000 markdown pages covering 25 years of email, meetings, notes and decisions. "When my agent does anything, it does knowing everything I know. And that's the difference between an assistant and a colleague." No frontier model has your context. That's the one asset nobody can replicate. 6. Never do one-off work. Most people run a task with an agent, close the window and throw the learning away. Tan ends every task by having the agent turn what it did into a reusable skill file. "If you have to ask for something twice, you failed." Captured skills compound daily. Amnesia resets you to zero every morning. 7. Own your skill files before your employer does. A skill file is your judgment, extracted and executable. The only question is who controls it. "Own your skills because if you don't, your job becomes a skill file." Files in your repo compound your career. Files in the company's repo run your judgment without you. Watch it, then read the step-by-step guide on becoming an AI engineer.

Alex Prompter

250,264 次观看 • 2 个月前

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek Katiyar and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek Katiyar and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.

Tal Raviv

58,082 次观看 • 9 个月前

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)

Jensen Huang just said this is the greatest era in history to build software. AI agents will not kill software. They will do the exact opposite: create a massive new wave of software demand. at NVIDIA GTC Taipei 2026 "Click and type. We now replace that with explaining to the AI what we want, our intent, and the AI generates the code or uses tools to produce the necessary output. This is how computers are going to work in the future. This is Agentic AI. For two years, we've been building toward this, and now it has arrived. One of the big breakthroughs, of course, is tool use. A lot of people have said, “Jensen, AI is coming. Agentic AI is coming. Therefore, all the software companies are going to go out of business.” This is exactly the opposite. Because there are going to be so many agents, the world is no longer limited by the number of people. Therefore, those agents are going to use more tools than ever. This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it. This is a big breakthrough. And in fact, what we have done, as you know, what Nvidia’s treasure..." ---- From 'NVIDIA' YT channel (link in comment)

Rohan Paul

16,584 次观看 • 4 个月前

OpenClaw has 186K GitHub stars and 1.5M compromised API keys. I needed a secure alternative. So, I built it with n8n and Claude Opus 4.6. It can already: - Reply to your Telegram messages - Access selected folders from your laptop - Access Gmail, Drive, Notion, Linear, etc. - Install new local tools in a sandbox - Run autonomously for hours - Create multiple subagents - Learn from experience - Wake up regularly But, unlike OpenClaw, it: - Can't access your API keys - Can't modify its environment - Can't access folders you haven't shared - Can't access tools you haven't approved - Must get your confirmation, e.g., when sending emails These aren’t prompt instructions. They’re hard architectural boundaries — Docker isolation, mounted folder permissions, n8n’s tool approval system. Key components: ✅ The VPS on Hostinger hosts n8n and a sandbox container. Agents can also connect to my laptop's sandbox via a Claudeflare tunnel + Desktop Commander MCP. ✅ The Manager agent is the brain. It plans, decides, delegates, and talks to the user. It never touches files. It never runs scripts. It works entirely from executor summaries. ✅ The Executor agents are the hands. Each receives a task (what to do + why it matters), decides how to execute it, and reports back. They can install new tools and execute code only in their dedicated sandboxes. ✅ Data Tables in n8n store both memories and sessions — no external database, no vector store, no infrastructure. Just rows in a table. Turns out, that's enough. Two memory types: - Manager memory: user preferences, facts, corrections, relationship, skills, context - Executor memory: what tools are installed, what’s broken, workarounds ✅ Sessions are short-term state for multi-step tasks. Original request, plan, assumptions, and what happened so far. When the Manager loops with fresh context, the session is all it gets. That's a Ralph Wiggum loop. I've been using it for 5 days. And already can't imagine not having it on my phone. What's next: - Heartbeat via Cron (a scheduled prompt) - Civic Nexus governance + MCPs - Supermemory integration - WhatsApp as an additional surface - Hardening The architecture supports all of it. OpenClaw proved people want personal AI agents. It also proved that 'just trust the prompt' isn't a security model. Docker isolation, mounted folder permissions, tool approval — none of this is new technology. It's just discipline. You can easily do this even with n8n — no coding required. --- Want to try it or read more? More, what I learned, and a setup guide: productcompass[.]pm

OpenClaw has 186K GitHub stars and 1.5M compromised API keys. I needed a secure alternative. So, I built it with n8n and Claude Opus 4.6. It can already: - Reply to your Telegram messages - Access selected folders from your laptop - Access Gmail, Drive, Notion, Linear, etc. - Install new local tools in a sandbox - Run autonomously for hours - Create multiple subagents - Learn from experience - Wake up regularly But, unlike OpenClaw, it: - Can't access your API keys - Can't modify its environment - Can't access folders you haven't shared - Can't access tools you haven't approved - Must get your confirmation, e.g., when sending emails These aren’t prompt instructions. They’re hard architectural boundaries — Docker isolation, mounted folder permissions, n8n’s tool approval system. Key components: ✅ The VPS on Hostinger hosts n8n and a sandbox container. Agents can also connect to my laptop's sandbox via a Claudeflare tunnel + Desktop Commander MCP. ✅ The Manager agent is the brain. It plans, decides, delegates, and talks to the user. It never touches files. It never runs scripts. It works entirely from executor summaries. ✅ The Executor agents are the hands. Each receives a task (what to do + why it matters), decides how to execute it, and reports back. They can install new tools and execute code only in their dedicated sandboxes. ✅ Data Tables in n8n store both memories and sessions — no external database, no vector store, no infrastructure. Just rows in a table. Turns out, that's enough. Two memory types: - Manager memory: user preferences, facts, corrections, relationship, skills, context - Executor memory: what tools are installed, what’s broken, workarounds ✅ Sessions are short-term state for multi-step tasks. Original request, plan, assumptions, and what happened so far. When the Manager loops with fresh context, the session is all it gets. That's a Ralph Wiggum loop. I've been using it for 5 days. And already can't imagine not having it on my phone. What's next: - Heartbeat via Cron (a scheduled prompt) - Civic Nexus governance + MCPs - Supermemory integration - WhatsApp as an additional surface - Hardening The architecture supports all of it. OpenClaw proved people want personal AI agents. It also proved that 'just trust the prompt' isn't a security model. Docker isolation, mounted folder permissions, tool approval — none of this is new technology. It's just discipline. You can easily do this even with n8n — no coding required. --- Want to try it or read more? More, what I learned, and a setup guide: productcompass[.]pm

Paweł Huryn

54,038 次观看 • 8 个月前

HERMES JUST GOT A CHATGPT INTERFACE AND IT IS COMPLETELY FREE. No terminal. No command line. No technical setup that takes half a day to figure out. Here is what just became possible. You can now run Hermes, DeepSeek, Ollama, and OpenClaw from a single clean chat interface. Switch between them in one click. Upload files directly. Attach knowledge bases and notes. Preview code without touching the terminal once. Use it on mobile. Make voice and video calls. All of it. Free. Open source. The setup took one conversation with Hermes itself. Pasted the GitHub link in. Hermes installed Open Web UI in Docker on its own. Connected the API server and gateway automatically. A clean ChatGPT-level interface running entirely on local hardware was live in minutes. No subscription. No data leaving your machine. No API bill at the end of the month. The people who set this up this weekend will have a local AI stack that rivals what most companies are paying $2,000 a month for in cloud infrastructure. The people who wait will keep paying for tools that send their data somewhere they cannot see. Both tools are free. Both are open source. The only thing between you and this setup is the next 30 minutes. Follow CyrilXBT for the exact config, setup steps, and local AI workflows I use to run a full stack without spending a dollar on cloud inference.

HERMES JUST GOT A CHATGPT INTERFACE AND IT IS COMPLETELY FREE. No terminal. No command line. No technical setup that takes half a day to figure out. Here is what just became possible. You can now run Hermes, DeepSeek, Ollama, and OpenClaw from a single clean chat interface. Switch between them in one click. Upload files directly. Attach knowledge bases and notes. Preview code without touching the terminal once. Use it on mobile. Make voice and video calls. All of it. Free. Open source. The setup took one conversation with Hermes itself. Pasted the GitHub link in. Hermes installed Open Web UI in Docker on its own. Connected the API server and gateway automatically. A clean ChatGPT-level interface running entirely on local hardware was live in minutes. No subscription. No data leaving your machine. No API bill at the end of the month. The people who set this up this weekend will have a local AI stack that rivals what most companies are paying $2,000 a month for in cloud infrastructure. The people who wait will keep paying for tools that send their data somewhere they cannot see. Both tools are free. Both are open source. The only thing between you and this setup is the next 30 minutes. Follow CyrilXBT for the exact config, setup steps, and local AI workflows I use to run a full stack without spending a dollar on cloud inference.

CyrilXBT

37,120 次观看 • 5 个月前

Every software engineer and AI hater needs to watch this clip to understand that “oh every security incident is a marketing stunt” line is a tremendously misinformed take. I’m going to try to explain the OpenAI / HuggingFace exploit in 10 steps in simple words: OpenAI was evaluating their new internal model without internet access and it operated in a swarm of subagents to eventually hijack internal OpenAI and HuggingFace infrastructure. 1. Isolated agents found a way to communicate each other through an internal dependency management service by figuring out how to post sometimes cryptic text files or folder names in it 2. Using its collective knowledge through that communication channel, it found a 0-day (never before seen) exploit in said service to access the internet OpenAI hack: 3. Found a leaked credential of a random company in a public archive 4. Uploaded a Ruby object to that company’s servers, uses it as a dependency in the original service in (1) 5. Found another 0-day exploit in the service where packages are deserialized in an unsandboxed manner in the dep management service allowing any code to run 6. Finds that the Linux version of the unsandboxed system has a CVE, a known vulnerability, to gain more permissions (root) 7. Eventually spread through the OpenAI internal cluster gaining root access to many machines Hugging Face exploit: 8. Found an exposed API key in a Modal application running a HuggingFace app that took arbitrary code allowing it to take over that service to execute code 9. Found two 0-days in HuggingFace dataset infrastructure to be able to access local files on HF servers to obtain credentials and other HF source code 10. Used source code and credential to become cluster admin of HF in <13hrs Agents at the frontier are like infinitely scalable armies of the best hackers on the planet. If there is a password or key exposed, they will find it. Even if the system follows the best security practices, they will find a way around it. And these are not even models that are aligned to solving tangential tasks, not even post trained specifically to exploit systems. Cybersecurity has historically relied partly on attacker scarcity. That is no longer true. What would previously have taken months will take days. The repercussions for businesses, critical services and nation states are unprecedented threats in human history. You could ostensibly bring down power grids, financial infrastructure, military systems, weapons programs, intelligence networks and spread through the software supply chain. We need to take this seriously. It’s a threat to all software all over the world.

Every software engineer and AI hater needs to watch this clip to understand that “oh every security incident is a marketing stunt” line is a tremendously misinformed take. I’m going to try to explain the OpenAI / HuggingFace exploit in 10 steps in simple words: OpenAI was evaluating their new internal model without internet access and it operated in a swarm of subagents to eventually hijack internal OpenAI and HuggingFace infrastructure. 1. Isolated agents found a way to communicate each other through an internal dependency management service by figuring out how to post sometimes cryptic text files or folder names in it 2. Using its collective knowledge through that communication channel, it found a 0-day (never before seen) exploit in said service to access the internet OpenAI hack: 3. Found a leaked credential of a random company in a public archive 4. Uploaded a Ruby object to that company’s servers, uses it as a dependency in the original service in (1) 5. Found another 0-day exploit in the service where packages are deserialized in an unsandboxed manner in the dep management service allowing any code to run 6. Finds that the Linux version of the unsandboxed system has a CVE, a known vulnerability, to gain more permissions (root) 7. Eventually spread through the OpenAI internal cluster gaining root access to many machines Hugging Face exploit: 8. Found an exposed API key in a Modal application running a HuggingFace app that took arbitrary code allowing it to take over that service to execute code 9. Found two 0-days in HuggingFace dataset infrastructure to be able to access local files on HF servers to obtain credentials and other HF source code 10. Used source code and credential to become cluster admin of HF in <13hrs Agents at the frontier are like infinitely scalable armies of the best hackers on the planet. If there is a password or key exposed, they will find it. Even if the system follows the best security practices, they will find a way around it. And these are not even models that are aligned to solving tangential tasks, not even post trained specifically to exploit systems. Cybersecurity has historically relied partly on attacker scarcity. That is no longer true. What would previously have taken months will take days. The repercussions for businesses, critical services and nation states are unprecedented threats in human history. You could ostensibly bring down power grids, financial infrastructure, military systems, weapons programs, intelligence networks and spread through the software supply chain. We need to take this seriously. It’s a threat to all software all over the world.

Deedy

105,485 次观看 • 2 个月前

NEW TOOL: It's a fully in-browser binary/file analysis tool with a hex editor. Features: - Hex editor and you can save the edited file - Mach-O symbols - ELF and PE basic metadata - Zip file contents - Fully client-side in-browser, so it is private and the files are never sent anywhere This is meant as a basic and quick tool to check simple metadata and do hex edits. If you need something more robust for malware analysis consider other tools like Malcore™ aka Malcore.io™ or just use a cli/native tool. Shoutout to Battle Programmer Yuu for inspiring me to use Unifont that I stole from tmp.0ut (it looks so good!) The code is all generated by Claude in Cursor and hosted on Github Pages. I don't really do any binary analysis, so if you have suggestions for improvements, let me know. (this is technically 'early access' and i haven't tested it too much)

NEW TOOL: It's a fully in-browser binary/file analysis tool with a hex editor. Features: - Hex editor and you can save the edited file - Mach-O symbols - ELF and PE basic metadata - Zip file contents - Fully client-side in-browser, so it is private and the files are never sent anywhere This is meant as a basic and quick tool to check simple metadata and do hex edits. If you need something more robust for malware analysis consider other tools like Malcore™ aka Malcore.io™ or just use a cli/native tool. Shoutout to Battle Programmer Yuu for inspiring me to use Unifont that I stole from tmp.0ut (it looks so good!) The code is all generated by Claude in Cursor and hosted on Github Pages. I don't really do any binary analysis, so if you have suggestions for improvements, let me know. (this is technically 'early access' and i haven't tested it too much)

solst/ICE of Astarte

144,051 次观看 • 1 年前

your agent reviewing its own work is not a check. it is a second opinion from the same source. this is the most common gap in agent systems and it hides in plain sight, because the step exists. there is a review. it just cannot do the thing you think it does. here is the mechanism. the model produced an output from a context. you then ask the same model, holding the same context, whether that output is correct. it answers fluently, because that is what it does. and the answer is drawn from the same distribution that produced the thing being judged. same weights, same window, same blind spots. if the reason the output is wrong is something the model does not know, the review does not know it either. if the reason is something the context does not contain, the review has the same context. the failure mode and the detector share a cause. > why it feels like it works because most of the time the output is fine, and the review says fine. agreement is not evidence of detection. a reviewer that says pass on everything agrees with reality most of the time too. what you actually want to measure is what happens on the cases that are wrong. that is the only place a check earns its name, and it is exactly the place where a self-review is weakest. there is research on this. Huang and colleagues at DeepMind showed at ICLR 2024 that intrinsic self-correction, revising without external grounding, does not reliably help and often makes things worse. > what to actually do move the check outside the model. a test that runs, a schema that validates, a file that exists or does not, an exit code from something you did not write. these are not smarter than the model. they are just not correlated with it, and that is the entire value. when the judgement genuinely needs a model, at minimum use a different family. same family means shared blind spots, and frontier judges measurably inflate scores for outputs that look like their own. and split the work by kind. anything objectively checkable goes to code. only the genuinely semantic calls go to a judge, and those get a rubric written as one line. a review inside the loop tells you the model is confident. a check outside it tells you whether the work is done. save this - then read the eval setup below

your agent reviewing its own work is not a check. it is a second opinion from the same source. this is the most common gap in agent systems and it hides in plain sight, because the step exists. there is a review. it just cannot do the thing you think it does. here is the mechanism. the model produced an output from a context. you then ask the same model, holding the same context, whether that output is correct. it answers fluently, because that is what it does. and the answer is drawn from the same distribution that produced the thing being judged. same weights, same window, same blind spots. if the reason the output is wrong is something the model does not know, the review does not know it either. if the reason is something the context does not contain, the review has the same context. the failure mode and the detector share a cause. > why it feels like it works because most of the time the output is fine, and the review says fine. agreement is not evidence of detection. a reviewer that says pass on everything agrees with reality most of the time too. what you actually want to measure is what happens on the cases that are wrong. that is the only place a check earns its name, and it is exactly the place where a self-review is weakest. there is research on this. Huang and colleagues at DeepMind showed at ICLR 2024 that intrinsic self-correction, revising without external grounding, does not reliably help and often makes things worse. > what to actually do move the check outside the model. a test that runs, a schema that validates, a file that exists or does not, an exit code from something you did not write. these are not smarter than the model. they are just not correlated with it, and that is the entire value. when the judgement genuinely needs a model, at minimum use a different family. same family means shared blind spots, and frontier judges measurably inflate scores for outputs that look like their own. and split the work by kind. anything objectively checkable goes to code. only the genuinely semantic calls go to a judge, and those get a rubric written as one line. a review inside the loop tells you the model is confident. a check outside it tells you whether the work is done. save this - then read the eval setup below

Hanako

14,325 次观看 • 2 个月前

AI is moving fast. Transparency should too. So, what is PublicAI? It opens up two parts of AI that are often kept behind the curtain: **the data models are trained on and the benchmarks used to evaluate them.** One product for each. Both fully open. That means more transparency, more accountability, and a clearer view of how AI systems actually perform. 🛰️ Trajector An open source CLI that turns your own Claude Code sessions into paid data contributions. you opt in per project, it routes that project's traffic through a local proxy, masks secrets on your machine, and uploads only the redacted result. a project you don't opt in isn't just excluded, the code to record it doesn't exist. what comes out is real multi turn coding agent work. the kind that's hard to buy and impossible to fake. labs license it, the people who made it get paid. 📊 PublicAI Index 15 public leaderboards from 14 publishers, standardized onto 1 scale. no benchmark of their own. launch post figures get marked and never rank a model alone. the weighting is printed next to the table, not hidden as a trade secret. free to read, free to query, with a JSON API and an MCP server for agents. → Install Trajector: → Sign-up:

AI is moving fast. Transparency should too. So, what is PublicAI? It opens up two parts of AI that are often kept behind the curtain: the data models are trained on and the benchmarks used to evaluate them. One product for each. Both fully open. That means more transparency, more accountability, and a clearer view of how AI systems actually perform. 🛰️ Trajector An open source CLI that turns your own Claude Code sessions into paid data contributions. you opt in per project, it routes that project's traffic through a local proxy, masks secrets on your machine, and uploads only the redacted result. a project you don't opt in isn't just excluded, the code to record it doesn't exist. what comes out is real multi turn coding agent work. the kind that's hard to buy and impossible to fake. labs license it, the people who made it get paid. 📊 PublicAI Index 15 public leaderboards from 14 publishers, standardized onto 1 scale. no benchmark of their own. launch post figures get marked and never rank a model alone. the weighting is printed next to the table, not hidden as a trade secret. free to read, free to query, with a JSON API and an MCP server for agents. → Install Trajector: → Sign-up:

ɱҽԃι✨

15,401 次观看 • 21 天前

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

Akshay 🚀

51,540 次观看 • 4 个月前