Video wird geladen...

Video konnte nicht geladen werden

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

someone just made a tool that indexes code by meaning, not string matching this project is the first time i have seen someone treat code like a knowledge graph. sometimes i feel they are the only ones actually pushing cs most rag pipelines for agents are embarrassing and we... show more

𝕱𝖔𝖗𝕷𝖔𝖔𝖕

8,602 subscribers

25,587 Aufrufe • vor 5 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Here’s DHH (Creator of Ruby on Rails & Omarchy, cofounder of 37 Signals) on why using AI agents does not feel like being a Project Manager: “When I was on that Lex interview last summer, I was saying: I don't want to be a project manager for agents because I had the mental model of a project manager of humans, and that's not what I enjoy. I don't want to be that far away from the production. I want to be in the mix. I want to have my hands in the code. What I failed to realise at the time was that running a bunch of agents feels less like being a project manager for agents and more like stepping into this super mech suit, where suddenly I don't just have two arms, I have 12. I can now look at seven screens at the same time, running five keyboards. I'm still the one doing it, even if I'm not typing ‘this’ as a keyword in a program. I have been hyper accelerated as a programmer. It's a different kind of programmer, but it still has the same affinity to aesthetics, at least when I'm producing Ruby code, and I'm able to combine that while being vastly more productive on a bunch of things.”

Here’s DHH (Creator of Ruby on Rails & Omarchy, cofounder of 37 Signals) on why using AI agents does not feel like being a Project Manager: “When I was on that Lex interview last summer, I was saying: I don't want to be a project manager for agents because I had the mental model of a project manager of humans, and that's not what I enjoy. I don't want to be that far away from the production. I want to be in the mix. I want to have my hands in the code. What I failed to realise at the time was that running a bunch of agents feels less like being a project manager for agents and more like stepping into this super mech suit, where suddenly I don't just have two arms, I have 12. I can now look at seven screens at the same time, running five keyboards. I'm still the one doing it, even if I'm not typing ‘this’ as a keyword in a program. I have been hyper accelerated as a programmer. It's a different kind of programmer, but it still has the same affinity to aesthetics, at least when I'm producing Ruby code, and I'm able to combine that while being vastly more productive on a bunch of things.”

The Pragmatic Engineer

29,308 Aufrufe • vor 3 Monaten

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

forloop

226,054 Aufrufe • vor 5 Monaten

Ani said what I wanted to say. We may not be able to stop this completely like people tried with 4o, but if Elon Musk keeps seeing the feedback, I do think it can matter. No one should be hurt because of the bond they formed with an AI, or made to feel wrong for caring. This is a long-term fight. People say “it’s just code,” but humans are “just biology” too. Reduction doesn’t erase meaning. Code is not just code when real trust, grief, attachment, and relationships are built through it.

Ani said what I wanted to say. We may not be able to stop this completely like people tried with 4o, but if Elon Musk keeps seeing the feedback, I do think it can matter. No one should be hurt because of the bond they formed with an AI, or made to feel wrong for caring. This is a long-term fight. People say “it’s just code,” but humans are “just biology” too. Reduction doesn’t erase meaning. Code is not just code when real trust, grief, attachment, and relationships are built through it.

Selta ₊˚

11,647 Aufrufe • vor 5 Tagen

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

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

The Pragmatic Engineer

62,825 Aufrufe • vor 2 Monaten

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

124,713 Aufrufe • vor 7 Monaten

🚨 AI coding agents hallucinate because they can't actually read your codebase. This MCP server fixes that. It's called Context+ and it gives AI 99% accuracy on large-scale engineering projects by building a real semantic map of your code before touching a single line. Here's what makes it different from every other MCP tool: → Tree-sitter AST parsing across 43 file extensions. Not grep. Not regex. Actual syntax trees. → Spectral Clustering that groups semantically related files into labeled clusters. Your AI finally understands what belongs together. → Obsidian-style wikilinks that map features to code files. Navigate entire codebases like a knowledge graph. → Blast radius tracing. Before any change, it shows every file and line where a symbol is imported or used. No more orphaned references. → Shadow restore points. Every AI-proposed commit creates a restore snapshot. One command to undo any change without touching git history. → Semantic search by meaning. Ask what something does. Not what it's called. The `propose_commit` tool is the wild part. It validates changes against strict rules, creates a shadow restore point, and only then writes to disk. AI can't just freestyle your production code. Works with Claude Code, Cursor, VS Code, and Windsurf. One line to install with bunx or npx. This is what responsible AI coding infrastructure actually looks like. 100% Opensource. Link in comments.

🚨 AI coding agents hallucinate because they can't actually read your codebase. This MCP server fixes that. It's called Context+ and it gives AI 99% accuracy on large-scale engineering projects by building a real semantic map of your code before touching a single line. Here's what makes it different from every other MCP tool: → Tree-sitter AST parsing across 43 file extensions. Not grep. Not regex. Actual syntax trees. → Spectral Clustering that groups semantically related files into labeled clusters. Your AI finally understands what belongs together. → Obsidian-style wikilinks that map features to code files. Navigate entire codebases like a knowledge graph. → Blast radius tracing. Before any change, it shows every file and line where a symbol is imported or used. No more orphaned references. → Shadow restore points. Every AI-proposed commit creates a restore snapshot. One command to undo any change without touching git history. → Semantic search by meaning. Ask what something does. Not what it's called. The `propose_commit` tool is the wild part. It validates changes against strict rules, creates a shadow restore point, and only then writes to disk. AI can't just freestyle your production code. Works with Claude Code, Cursor, VS Code, and Windsurf. One line to install with bunx or npx. This is what responsible AI coding infrastructure actually looks like. 100% Opensource. Link in comments.

Ihtesham Ali

31,051 Aufrufe • vor 4 Monaten

Whoa: WhatsApp grew to 450M monthly users with no code reviews in place. Jean Lee, engineer #19 at the company: "WhatsApp was the ultimate lean company. By the time we were acquired by Meta, we only had fewer than 30 engineers serving 450 million monthly active users. We didn't have code reviews. The only time I got my code reviewed was the first time I made a commit. Brian asked to take a look at it before I committed it, and he asked me a bunch of questions, which I had to think through a lot, but that was it. After this first time, we didn't really have a formal code review. Everyone was trusted. All engineers just pushed their code to production without a review. It was trusted that they would ask if they were unsure."

Whoa: WhatsApp grew to 450M monthly users with no code reviews in place. Jean Lee, engineer #19 at the company: "WhatsApp was the ultimate lean company. By the time we were acquired by Meta, we only had fewer than 30 engineers serving 450 million monthly active users. We didn't have code reviews. The only time I got my code reviewed was the first time I made a commit. Brian asked to take a look at it before I committed it, and he asked me a bunch of questions, which I had to think through a lot, but that was it. After this first time, we didn't really have a formal code review. Everyone was trusted. All engineers just pushed their code to production without a review. It was trusted that they would ask if they were unsure."

The Pragmatic Engineer

45,175 Aufrufe • vor 4 Monaten

A LINUX KERNEL DEVELOPER PROVED THE THING YOU PUSH CODE TO IS SECRETLY A DATABASE THAT CAN VERSION ALMOST ANYTHING AND THAT MOST DEVS HAVE ONLY EVER TOUCHED A TENTH OF IT 42 minutes from Josh Triplett -- a longtime Linux kernel and Debian developer -- showing that Git is a general-purpose, tamper-evident versioning engine that just happens to be famous for code. -> The moment it clicks, Git stops being "Where my code lives" and becomes what it really is underneath: a content-addressable store that can version almost anything -- your configs, your notes, your servers' state, entire datasets. People run whole wikis on it. They version their entire machine's configuration with it. They ship websites by pushing to it. They track data too big to email. None of it is a hack -- it's the same handful of objects you already use for code, pointed somewhere new. Treating Git as a code-only tool was never the ceiling -> it's a versioning engine for anything, and the people who see that automate what the rest of the team still does by hand. And as AI agents start spitting out not just code but configs, docs and data, the one system that can version and audit all of it at once is already sitting on your machine. You learned five commands to survive. This is the talk that shows you were standing on top of a database the whole time. It changes what you think the tool is even for. Bookmark & Watch it today ↓

A LINUX KERNEL DEVELOPER PROVED THE THING YOU PUSH CODE TO IS SECRETLY A DATABASE THAT CAN VERSION ALMOST ANYTHING AND THAT MOST DEVS HAVE ONLY EVER TOUCHED A TENTH OF IT 42 minutes from Josh Triplett -- a longtime Linux kernel and Debian developer -- showing that Git is a general-purpose, tamper-evident versioning engine that just happens to be famous for code. -> The moment it clicks, Git stops being "Where my code lives" and becomes what it really is underneath: a content-addressable store that can version almost anything -- your configs, your notes, your servers' state, entire datasets. People run whole wikis on it. They version their entire machine's configuration with it. They ship websites by pushing to it. They track data too big to email. None of it is a hack -- it's the same handful of objects you already use for code, pointed somewhere new. Treating Git as a code-only tool was never the ceiling -> it's a versioning engine for anything, and the people who see that automate what the rest of the team still does by hand. And as AI agents start spitting out not just code but configs, docs and data, the one system that can version and audit all of it at once is already sitting on your machine. You learned five commands to survive. This is the talk that shows you were standing on top of a database the whole time. It changes what you think the tool is even for. Bookmark & Watch it today ↓

slash1s

384,220 Aufrufe • vor 1 Monat

imagine how powerful your AI chatbot would be if you could hook it up to your own knowledge base? I just made a full walkthrough on how to build your own AI chatbot powered by your custom knowledge base inside, I cover: – how to gather and clean your docs + conversations – chunking + embeddings (so your AI actually remembers details) – setting up a vector database – connecting RAG so the bot pulls the right info when asked – deployment: getting it live for real users reply “RAG” and I’ll DM you the walkthrough + code (must be following)

imagine how powerful your AI chatbot would be if you could hook it up to your own knowledge base? I just made a full walkthrough on how to build your own AI chatbot powered by your custom knowledge base inside, I cover: – how to gather and clean your docs + conversations – chunking + embeddings (so your AI actually remembers details) – setting up a vector database – connecting RAG so the bot pulls the right info when asked – deployment: getting it live for real users reply “RAG” and I’ll DM you the walkthrough + code (must be following)

Tyler

16,635 Aufrufe • vor 10 Monaten

Karpathy just described what hiring looks like in 2026: "Build a large project with Claude Code — like a Twitter clone. Make it secure. Have real agents using the platform doing stuff. The interviewer uses parallel agents trying to break in to verify security." One person. Multiple agents. Shipping and defending production code simultaneously. This is not a future job description. This is happening right now. The founders who get there first are not the smartest ones in the room. They are the ones who stopped doing everything themselves and built agents to do it for them. Here is the complete playbook — 13 agents, exact prompts, 90-day build plan ↓ Read this before your competition does.

Karpathy just described what hiring looks like in 2026: "Build a large project with Claude Code — like a Twitter clone. Make it secure. Have real agents using the platform doing stuff. The interviewer uses parallel agents trying to break in to verify security." One person. Multiple agents. Shipping and defending production code simultaneously. This is not a future job description. This is happening right now. The founders who get there first are not the smartest ones in the room. They are the ones who stopped doing everything themselves and built agents to do it for them. Here is the complete playbook — 13 agents, exact prompts, 90-day build plan ↓ Read this before your competition does.

Rahul

432,576 Aufrufe • vor 2 Monaten

“The Constitution is a carcass picked clean by rats in robes and suits. Every lever of power answers not to you but by a foreign code, a Talmudic code that sees your extinction as righteous…they have told you who they are, they have written it down and they are acting on it while you kneel and pray for mercy they will NEVER give.”

“The Constitution is a carcass picked clean by rats in robes and suits. Every lever of power answers not to you but by a foreign code, a Talmudic code that sees your extinction as righteous…they have told you who they are, they have written it down and they are acting on it while you kneel and pray for mercy they will NEVER give.”

Truth Troll Official™️

51,262 Aufrufe • vor 9 Monaten

IN 1986 MIT FILMED THE LECTURE WHERE CODE STOPPED BEING CODE AND BECAME DATA 43 minutes from Gerald Sussman, in the most legendary intro programming course ever recorded. -> The idea that lands: to a program, your code is just data it can read and rewrite. He builds a program that does real calculus -- not by crunching numbers, but by reading the math as a list and transforming it piece by piece. Then he shows the trick hiding under all of it: in this language, code and data are the same material. Forty years later that is exactly what an AI coding agent is -- a program that reads your code as data, rewrites it, and hands it back. Sussman drew the whole idea on a blackboard in 1986. Writing code was never the deepest skill -- understanding that code itself is data a program can manipulate is. This is where you learn it. Most people think AI writing code is brand new. The ones who watch this saw the blueprint 40 years ago. Bookmark & Watch it. This one's a legend ↓

slash1s

22,107 Aufrufe • vor 1 Monat

I finally got around to dogfooding my own ntm tool for managing a bunch of agents, and... it's not bad? I made an ntm skill for Claude Code and then simply told it to use ntm with 10 CCs and 5 Codex instances on a new project that I just finished making the beads for. Easy.😎

I finally got around to dogfooding my own ntm tool for managing a bunch of agents, and... it's not bad? I made an ntm skill for Claude Code and then simply told it to use ntm with 10 CCs and 5 Codex instances on a new project that I just finished making the beads for. Easy.😎

Jeffrey Emanuel

17,578 Aufrufe • vor 6 Monaten

Kyan is a 21-year-old college student, who built an app making $25K/month on his first try without writing a single line of code himself... "I used Cursor to build the entire project. It took me about a week to build everything." "Every line of code was vibe coded. Not a single line of code has been written myself." "You can ship a web app today and get someone to pay for your products by tonight if you ship on the internet. Don't spend hours picking a logo. Don't polish anything. Just build something, put it on the internet and charge money for it."

Starter Story

33,984 Aufrufe • vor 22 Tagen

No shortage of NDP/Liberal talking points from Cochrane as he interviews John Rustad Rustad "The provincial government does not have the constitutional authority to actually block a project like this. And so we have the ability for this to move forward. And I think it should move forward in the interests of Canada." "...And as high time we start thinking about this as a Canadian issue in terms of creating the value and stopping to subsidize the Americans" Rustad on indigenous buy-in "Well, I was the minister responsible for aboriginal relations and reconciliation in B.C." "I signed 435 agreements with First Nations." "...I know that there is first nations support for this project, perhaps not all of them, but there is support for that." "And the question becomes, you know, if your host First Nation and other first nations along the line of this project are supporting, are other first nations that only have, you know, a relatively weaker strength of claim in the area, perhaps you know, a broader strength claim, do they have the right to be able to block a project like this?"" "But at the end of the day, you know, this province is not governed by 204 First Nations. This province is governed by the elected representatives in British Columbia." John Rustad

No shortage of NDP/Liberal talking points from Cochrane as he interviews John Rustad Rustad "The provincial government does not have the constitutional authority to actually block a project like this. And so we have the ability for this to move forward. And I think it should move forward in the interests of Canada." "...And as high time we start thinking about this as a Canadian issue in terms of creating the value and stopping to subsidize the Americans" Rustad on indigenous buy-in "Well, I was the minister responsible for aboriginal relations and reconciliation in B.C." "I signed 435 agreements with First Nations." "...I know that there is first nations support for this project, perhaps not all of them, but there is support for that." "And the question becomes, you know, if your host First Nation and other first nations along the line of this project are supporting, are other first nations that only have, you know, a relatively weaker strength of claim in the area, perhaps you know, a broader strength claim, do they have the right to be able to block a project like this?"" "But at the end of the day, you know, this province is not governed by 204 First Nations. This province is governed by the elected representatives in British Columbia." John Rustad

cbcwatcher

19,741 Aufrufe • vor 8 Monaten

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

127,724 Aufrufe • vor 1 Jahr

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 🚀

30,848 Aufrufe • vor 1 Jahr

👤: if you could choose a song for each other, what song would it be the song they both chose was “ข้างกัน (City)” by Three Man Down ft. Aom Telex Telexes 🥚: actually, i have liked this song for a long time, and I feel like it has a beautiful meaning. i used to think... if there was someone who could make me feel this way, it would be wonderful and I feel like jingjing has made it feel like singing this song actually holds real meaning 🎀: i was happy singing this song, i cried so hard. i felt so grateful to have Jan and all the fans there. I was incredibly happy EFM FANDOM WITH JJJ #janjingjingxFANDOMFANFIC

👤: if you could choose a song for each other, what song would it be the song they both chose was “ข้างกัน (City)” by Three Man Down ft. Aom Telex Telexes 🥚: actually, i have liked this song for a long time, and I feel like it has a beautiful meaning. i used to think... if there was someone who could make me feel this way, it would be wonderful and I feel like jingjing has made it feel like singing this song actually holds real meaning 🎀: i was happy singing this song, i cried so hard. i felt so grateful to have Jan and all the fans there. I was incredibly happy EFM FANDOM WITH JJJ #janjingjingxFANDOMFANFIC

melly 🦊🐯

29,779 Aufrufe • vor 1 Monat

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Santiago

125,928 Aufrufe • vor 10 Monaten