Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

What a fun little breakfast chat with swyx Windsurf just released Fast Context. Unlike traditional agentic search, Fast Context searches and retrieves relevant code from your codebase 20x faster. Game changing for developers who want to stay in flow. Watch it in action inside Andrej Karpathy’s nanochat repo. All...

MilksandMatcha's profile picture

Sarah Chieng

23,775 subscribers

397,034 görüntüleme • 9 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

ok so let me explain why subagents kill long context Like you can spend $500m building 100 million context models, and they would be 1) slow, 2) expensive to use, 3) have huge context rot. O(n) is the lower bound. Cog's approach is something you learn in day 1 of CS50 - divide and parallelize. Embeddings are too dumb, Agentic Search is too slow. So train limited-agency (max 4 turns), natively parallel tool calling (avg parallelism of 7-8, custom toolset) fast (2800tok/s) subagents to give the performance of Agentic Search under an acceptable "Flow Window" that feels immaterially slower than Embeddings. The benefit of this is threefold: - 8 ^ 4 toolcalls cover a very large code search space. can compound subagent calls if more needed. - predictable cost & end to end latency - subagent outputs "clean" contexts, free of context failure modes like context poisoning and context rot (h/t Drew Breunig ) we originally called this Rapid Agentic Search, to contrast with RAG. but Fast Context rolls of the tongue better. there's 2 other perspectives that are worthwhile, i'll go into below, but just go try it out. here it is on Andrej Karpathy's fastchat
1:23

ok so let me explain why subagents kill long context Like you can spend $500m building 100 million context models, and they would be 1) slow, 2) expensive to use, 3) have huge context rot. O(n) is the lower bound. Cog's approach is something you learn in day 1 of CS50 - divide and parallelize. Embeddings are too dumb, Agentic Search is too slow. So train limited-agency (max 4 turns), natively parallel tool calling (avg parallelism of 7-8, custom toolset) fast (2800tok/s) subagents to give the performance of Agentic Search under an acceptable "Flow Window" that feels immaterially slower than Embeddings. The benefit of this is threefold: - 8 ^ 4 toolcalls cover a very large code search space. can compound subagent calls if more needed. - predictable cost & end to end latency - subagent outputs "clean" contexts, free of context failure modes like context poisoning and context rot (h/t Drew Breunig ) we originally called this Rapid Agentic Search, to contrast with RAG. but Fast Context rolls of the tongue better. there's 2 other perspectives that are worthwhile, i'll go into below, but just go try it out. here it is on Andrej Karpathy's fastchat

swyx 🇸🇬

276,060 görüntüleme • 9 ay önce

We just added Prompt Completions to Augment for VS Code. You’ll now get context-aware suggestions as you type prompts for your agent — including natural-language completions, variable names, file references, and more. It makes writing great prompts faster, especially for users who craft long specs or detailed instructions. Powered by full codebase context and agent history, so agent prompt completions feel in sync with what users are trying to write.
0:50

We just added Prompt Completions to Augment for VS Code. You’ll now get context-aware suggestions as you type prompts for your agent — including natural-language completions, variable names, file references, and more. It makes writing great prompts faster, especially for users who craft long specs or detailed instructions. Powered by full codebase context and agent history, so agent prompt completions feel in sync with what users are trying to write.

Augment Code

593,917 görüntüleme • 8 ay önce

INTRODUCING FACTORY Factory is the Command Center where developers and agentic AI collaborate to understand, plan, and build enterprise software. Our enterprise platform combines advanced engineering system indexing, state-of-the-art retrieval and search, and reliable agentic systems powered by frontier LLMs. In your Factory, • 🤖 Droid Mode unlocks cutting-edge agentic capabilities. Accelerate your development with AI that autonomously pulls in tickets, reads error logs, retrieves relevant context, executes code, and solves complex, long-running tasks. • 🪡 Threads let you jump into deep work with all relevant context dynamically surfaced in front of you. No more crawling through Github, Slack, Google Drive, Notion, Jira, Slack, or context-switching between them. • ⚡ Workflows transform and centralize your organization’s best practices into executable, AI-powered processes. Automate repetitive tasks like building integrations, bug-fixing, PRD creation, release notes, version updates, and more. We're working with some of the most innovative organizations in software — from AI-forward enterprises like MongoDB to high-growth organizations across the world. Our enterprise platform combines advanced engineering system indexing, state-of-the-art retrieval and search, and reliable agentic systems using frontier LLMs like o3 and Claude 3.7 Sonnet 1/7
0:57

INTRODUCING FACTORY Factory is the Command Center where developers and agentic AI collaborate to understand, plan, and build enterprise software. Our enterprise platform combines advanced engineering system indexing, state-of-the-art retrieval and search, and reliable agentic systems powered by frontier LLMs. In your Factory, • 🤖 Droid Mode unlocks cutting-edge agentic capabilities. Accelerate your development with AI that autonomously pulls in tickets, reads error logs, retrieves relevant context, executes code, and solves complex, long-running tasks. • 🪡 Threads let you jump into deep work with all relevant context dynamically surfaced in front of you. No more crawling through Github, Slack, Google Drive, Notion, Jira, Slack, or context-switching between them. • ⚡ Workflows transform and centralize your organization’s best practices into executable, AI-powered processes. Automate repetitive tasks like building integrations, bug-fixing, PRD creation, release notes, version updates, and more. We're working with some of the most innovative organizations in software — from AI-forward enterprises like MongoDB to high-growth organizations across the world. Our enterprise platform combines advanced engineering system indexing, state-of-the-art retrieval and search, and reliable agentic systems using frontier LLMs like o3 and Claude 3.7 Sonnet 1/7

Factory

327,877 görüntüleme • 1 yıl önce

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:
0:46

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 görüntüleme • 5 ay önce

We built MiniMax a CLI coding agent like Claude Code, powered by MiniMax M3. It can: → Read files → Write code → Run shell commands autonomously → Understand large codebases with long-context reasoning → Handle real multi-file engineering tasks → Work entirely inside your terminal And it's fully hackable. Swap prompts. Add tools. Customize workflows. Make it your own. No GUI. Just code. Built for developers who live in the terminal.
1:07

We built MiniMax a CLI coding agent like Claude Code, powered by MiniMax M3. It can: → Read files → Write code → Run shell commands autonomously → Understand large codebases with long-context reasoning → Handle real multi-file engineering tasks → Work entirely inside your terminal And it's fully hackable. Swap prompts. Add tools. Customize workflows. Make it your own. No GUI. Just code. Built for developers who live in the terminal.

Darshal Jaitwar

18,861 görüntüleme • 1 ay önce

New course to bring you up to state-of-the-art at using AI to help you code: Build Apps with Windsurf's AI Coding Agents, built in partnership with WIndsurf (Codeium) and taught by Anshul Ramachandran! AI-assisted IDEs (Integrated Development Environments) make developers’ workflows faster, more efficient, and much more fun. Agentic tools like Windsurf are more than just code autocomplete—they are collaborative coding agents that help you break down complex applications, iterate efficiently, and generate code that spans multiple files. Although a lot of coding assistants share the same underlying large language models for planning and reasoning, a major point of distinction is how they handle tools, keep track of context, and stay aligned with your intent as a developer. For instance, if you make modifications to a class definition in your code and make the same modifications to other classes in the same directory, you might tell the AI agent "Do the same thing in similar places in this directory." Here, tracking your intent means understanding that “the same thing" refers to that recent edit you just made, which must be followed by appropriate search and tool-calling to implement the changes. In this course, you'll learn the inner workings of coding agents, their strengths and limitations, and how to use Windsurf to quickly build several applications. In detail, you'll: - Build a mental model of how agents work by combining human-action tracking, tool integration, and context awareness to carry out an agentic coding workflow. - Learn the challenges of code search and discovery and how a multi-step retrieval approach helps coding agents address them. - Use Windsurf to analyze and understand a large, old codebase and update it to the latest versions of the frameworks and packages it uses. - Build a Wikipedia data analysis app that retrieves, parses, and analyzes word frequencies. - Enhance the performance of your Wikipedia analysis app by adding caching, and through this, also learn how to course-correct when the AI agent produces unexpected results. - Learn tips and tricks such as keyboard shortcuts, autocomplete, and @ mentions to quickly call on agentic capabilities. - Use image/multimodal capabilities of the AI agent to increase your development velocity; you'll see an example of uploading a mockup with sketched-out UI features, and ask the agent to use that to build new functionality to an app. By the end of this course, you’ll understand agentic coding in-depth and know how to use it to make your development process much faster, more efficient, and enjoyable. Please sign up here!
4:01

New course to bring you up to state-of-the-art at using AI to help you code: Build Apps with Windsurf's AI Coding Agents, built in partnership with WIndsurf (Codeium) and taught by Anshul Ramachandran! AI-assisted IDEs (Integrated Development Environments) make developers’ workflows faster, more efficient, and much more fun. Agentic tools like Windsurf are more than just code autocomplete—they are collaborative coding agents that help you break down complex applications, iterate efficiently, and generate code that spans multiple files. Although a lot of coding assistants share the same underlying large language models for planning and reasoning, a major point of distinction is how they handle tools, keep track of context, and stay aligned with your intent as a developer. For instance, if you make modifications to a class definition in your code and make the same modifications to other classes in the same directory, you might tell the AI agent "Do the same thing in similar places in this directory." Here, tracking your intent means understanding that “the same thing" refers to that recent edit you just made, which must be followed by appropriate search and tool-calling to implement the changes. In this course, you'll learn the inner workings of coding agents, their strengths and limitations, and how to use Windsurf to quickly build several applications. In detail, you'll: - Build a mental model of how agents work by combining human-action tracking, tool integration, and context awareness to carry out an agentic coding workflow. - Learn the challenges of code search and discovery and how a multi-step retrieval approach helps coding agents address them. - Use Windsurf to analyze and understand a large, old codebase and update it to the latest versions of the frameworks and packages it uses. - Build a Wikipedia data analysis app that retrieves, parses, and analyzes word frequencies. - Enhance the performance of your Wikipedia analysis app by adding caching, and through this, also learn how to course-correct when the AI agent produces unexpected results. - Learn tips and tricks such as keyboard shortcuts, autocomplete, and @ mentions to quickly call on agentic capabilities. - Use image/multimodal capabilities of the AI agent to increase your development velocity; you'll see an example of uploading a mockup with sketched-out UI features, and ask the agent to use that to build new functionality to an app. By the end of this course, you’ll understand agentic coding in-depth and know how to use it to make your development process much faster, more efficient, and enjoyable. Please sign up here!

Andrew Ng

139,858 görüntüleme • 1 yıl önce

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.
0:31

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 🚀

30,850 görüntüleme • 1 yıl önce

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!
0:26

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Avi Chawla

11,927 görüntüleme • 4 ay önce

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or *agentically* create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!
0:38

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or *agentically* create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!

Jerry Liu

77,373 görüntüleme • 10 ay önce

Traditional (SQL) databases rely primarily on keyword-based searches to retrieve information. These searches match the exact words or phrases in your query to the text stored in the database. While effective for many applications, this method has limitations when it comes to understanding context or finding relevant information that doesn’t include the exact keywords. Hybrid search combines the strengths of traditional keyword-based BM25 search with the advanced capabilities of semantic search. To effectively implement a hybrid search, a vector database is essential. Vector databases go beyond just words; they understand the meaning behind the data. They transform data such as text, images, or audio into numerical representations called vectors. These vector embeddings enable the database to find similar items, even if they don't share exact keywords. When you integrate hybrid search with Retrieval-Augmented Generation (RAG) systems, you can achieve higher accuracy in retrieved context and better output in generated responses. Learn more about RAG systems in this video with Victoria Slocum:
0:44

Traditional (SQL) databases rely primarily on keyword-based searches to retrieve information. These searches match the exact words or phrases in your query to the text stored in the database. While effective for many applications, this method has limitations when it comes to understanding context or finding relevant information that doesn’t include the exact keywords. Hybrid search combines the strengths of traditional keyword-based BM25 search with the advanced capabilities of semantic search. To effectively implement a hybrid search, a vector database is essential. Vector databases go beyond just words; they understand the meaning behind the data. They transform data such as text, images, or audio into numerical representations called vectors. These vector embeddings enable the database to find similar items, even if they don't share exact keywords. When you integrate hybrid search with Retrieval-Augmented Generation (RAG) systems, you can achieve higher accuracy in retrieved context and better output in generated responses. Learn more about RAG systems in this video with Victoria Slocum:

Femke Plantinga

140,618 görüntüleme • 2 yıl önce

Cognition has signed a definitive agreement to acquire Windsurf. The acquisition includes Windsurf’s IP, product, trademark and brand, and strong business. Above all, it includes Windsurf’s world-class people, whom we’re privileged to welcome to our team. We are also honoring their talent and hard work in building Windsurf into the great business it is today. This transaction is structured so that 100% of Windsurf employees will participate financially. They will also have all vesting cliffs waived and will receive fully accelerated vesting for their work to date. At Cognition we have focused on developing robust and secure autonomous agents, while Windsurf has pioneered the agentic IDE. Devin + Windsurf are a powerful combination for the developers we serve. Working side by side, we’ll soon enable you to plan tasks in an IDE powered by Devin’s codebase understanding, delegate chunks of work to multiple Devins in parallel, complete the highest-leverage parts yourself with the help of autocomplete, and stitch it all back together in the same IDE. Cognition and Windsurf are united behind a shared vision for the future of software engineering, and there’s never been a better time to build. Welcome to our new colleagues from Windsurf!
1:13

Cognition has signed a definitive agreement to acquire Windsurf. The acquisition includes Windsurf’s IP, product, trademark and brand, and strong business. Above all, it includes Windsurf’s world-class people, whom we’re privileged to welcome to our team. We are also honoring their talent and hard work in building Windsurf into the great business it is today. This transaction is structured so that 100% of Windsurf employees will participate financially. They will also have all vesting cliffs waived and will receive fully accelerated vesting for their work to date. At Cognition we have focused on developing robust and secure autonomous agents, while Windsurf has pioneered the agentic IDE. Devin + Windsurf are a powerful combination for the developers we serve. Working side by side, we’ll soon enable you to plan tasks in an IDE powered by Devin’s codebase understanding, delegate chunks of work to multiple Devins in parallel, complete the highest-leverage parts yourself with the help of autocomplete, and stitch it all back together in the same IDE. Cognition and Windsurf are united behind a shared vision for the future of software engineering, and there’s never been a better time to build. Welcome to our new colleagues from Windsurf!

Cognition

3,049,713 görüntüleme • 1 yıl önce

New course: Spec-Driven Development with Coding Agents, built in partnership with JetBrains, and taught by Paul Everitt | @pauleveritt@fosstodon.org. Vibe coding is fast, but often produces code that doesn't match what you asked for. This short course teaches you spec-driven development: write a detailed spec defining what to build, and work with your coding agent to implement it. Many of the best developers already build this way. A spec lets you control large code changes with a few words, preserve context across agent sessions, and stay in control as your project grows in complexity. Skills you'll gain: - Write a detailed specification to define your mission, tech stack, and roadmap, giving your agent the context it needs from the start - Plan, implement, and validate features in iterative loops using a spec as your agent's guide - Apply the same repeatable workflow to both new and legacy codebases - Package your workflow into a portable agent skill that works across agents and IDEs Join and write specs that keep your coding agent on track!
2:51

New course: Spec-Driven Development with Coding Agents, built in partnership with JetBrains, and taught by Paul Everitt | @[email protected]. Vibe coding is fast, but often produces code that doesn't match what you asked for. This short course teaches you spec-driven development: write a detailed spec defining what to build, and work with your coding agent to implement it. Many of the best developers already build this way. A spec lets you control large code changes with a few words, preserve context across agent sessions, and stay in control as your project grows in complexity. Skills you'll gain: - Write a detailed specification to define your mission, tech stack, and roadmap, giving your agent the context it needs from the start - Plan, implement, and validate features in iterative loops using a spec as your agent's guide - Apply the same repeatable workflow to both new and legacy codebases - Package your workflow into a portable agent skill that works across agents and IDEs Join and write specs that keep your coding agent on track!

Andrew Ng

462,784 görüntüleme • 3 ay önce

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!
2:57

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

200,950 görüntüleme • 1 yıl önce

Have you tried AI Contextual Search inside OptimAI yet? Search isn’t just search anymore. We’ve rebuilt it from the ground up to feel like an intelligent signal detector inside the chaos of the internet. 🔍 AI Contextual Search now: • Understands meaning, not just keywords • Filters out noise and irrelevant posts automatically • Surfaces the exact insight you’re looking for • Learns from your context, domain, and intent • Works at scale thanks to the growing nodes - powering the OptimAI Network This is what happens when decentralized compute meets agentic intelligence - fast, deep, contextual understanding in real time. And yes… it’s already live. Show us the smartest search results your OptimAI agent found today. 😎 We’d love to see how far you can push it. 👉
0:35

Have you tried AI Contextual Search inside OptimAI yet? Search isn’t just search anymore. We’ve rebuilt it from the ground up to feel like an intelligent signal detector inside the chaos of the internet. 🔍 AI Contextual Search now: • Understands meaning, not just keywords • Filters out noise and irrelevant posts automatically • Surfaces the exact insight you’re looking for • Learns from your context, domain, and intent • Works at scale thanks to the growing nodes - powering the OptimAI Network This is what happens when decentralized compute meets agentic intelligence - fast, deep, contextual understanding in real time. And yes… it’s already live. Show us the smartest search results your OptimAI agent found today. 😎 We’d love to see how far you can push it. 👉

OptimAI

33,989 görüntüleme • 8 ay önce

A new short course, Claude Code: A Highly Agentic Coding Assistant, is live! Claude Code is currently one of the most capable coding assistants. It can explore your codebase, plan features, write tests, refactor code, and even collaborate across multiple sessions—with surprisingly minimal input. In this course, you’ll learn how to guide Claude Code effectively: from setting up context and memory to integrating with GitHub and MCP servers. You’ll use it to extend a RAG chatbot, refactor a Jupyter notebook for e-commerce data analysis, build a web app from a Figma design, and more. Taught by Elie Schoppik (Elie Schoppik) and built in collaboration with Anthropic, this course is a must for AI builders. 👉 Enroll now:
2:37

A new short course, Claude Code: A Highly Agentic Coding Assistant, is live! Claude Code is currently one of the most capable coding assistants. It can explore your codebase, plan features, write tests, refactor code, and even collaborate across multiple sessions—with surprisingly minimal input. In this course, you’ll learn how to guide Claude Code effectively: from setting up context and memory to integrating with GitHub and MCP servers. You’ll use it to extend a RAG chatbot, refactor a Jupyter notebook for e-commerce data analysis, build a web app from a Figma design, and more. Taught by Elie Schoppik (Elie Schoppik) and built in collaboration with Anthropic, this course is a must for AI builders. 👉 Enroll now:

DeepLearning.AI

32,513 görüntüleme • 1 yıl önce

Smarter Search. Deeper Context. Sharper Insight. We’re excited to introduce two powerful upgrades for OptimAI: AI Contextual Search and Tweet Radar. Try it today: AI Contextual Search helps you find exactly what matters. It filters out the noise and understands meaning, context, and intent to deliver the most accurate information from millions of sources. Perfect for research, discovery, and staying ahead. Tweet Radar lets you explore what’s trending, relevant, and worth your attention on X. You can now easily track narratives, find insights, and connect with the right conversations in seconds. Together, they mark the next step toward a truly intelligent, reasoning Agentic AI - one that saves time and amplifies your focus.
0:37

Smarter Search. Deeper Context. Sharper Insight. We’re excited to introduce two powerful upgrades for OptimAI: AI Contextual Search and Tweet Radar. Try it today: AI Contextual Search helps you find exactly what matters. It filters out the noise and understands meaning, context, and intent to deliver the most accurate information from millions of sources. Perfect for research, discovery, and staying ahead. Tweet Radar lets you explore what’s trending, relevant, and worth your attention on X. You can now easily track narratives, find insights, and connect with the right conversations in seconds. Together, they mark the next step toward a truly intelligent, reasoning Agentic AI - one that saves time and amplifies your focus.

OptimAI

29,787 görüntüleme • 8 ay önce

From zero to an MVP launch in 7 days Day 4 log Main feature: AI Medical Search (like Perplexity but for Health & Medical): - Specialized AI Search - Sources from highly reliable scientific reports - Smart answers powered by OpenAI and Anthropic AI depending on context - Custom Markdown rendering for AI responses - Async search + streaming AI for faster response times - No design, just simple UI to ship fast …and cook a lot of bugs 👨‍🍳 Marketing: - Still warming up TikTok accounts - Researching viral formats Day 4 = Build. Day 5 = Build. Day 6 = Still Build... ... Shipping > perfection. #BuildInPublic #shipaton2025
0:44

From zero to an MVP launch in 7 days Day 4 log Main feature: AI Medical Search (like Perplexity but for Health & Medical): - Specialized AI Search - Sources from highly reliable scientific reports - Smart answers powered by OpenAI and Anthropic AI depending on context - Custom Markdown rendering for AI responses - Async search + streaming AI for faster response times - No design, just simple UI to ship fast …and cook a lot of bugs 👨‍🍳 Marketing: - Still warming up TikTok accounts - Researching viral formats Day 4 = Build. Day 5 = Build. Day 6 = Still Build... ... Shipping > perfection. #BuildInPublic #shipaton2025

Alex Nguyen

19,563 görüntüleme • 11 ay önce

GROK CODE FAST 1 TAKES #1 ON OPENROUTER, DEVELOPERS PICK REAL PERFORMANCE OVER HYPE Grok Code Fast 1 just locked in the top spot on OpenRouter’s December 2025 monthly leaderboard, and this one actually matters. Real workloads. Real builders choosing what they trust when things break, scale, or need to ship. According to OpenRouter data, Grok Code Fast 1 processed billions of tokens in production, clearing every major competitor. Claude Sonnet 4, GPT-5 variants, Gemini, DeepSeek , all solid models, all left behind. Developers didn’t debate it on X. They just routed traffic. The reasons are practical, not philosophical. Grok Code Fast 1 is fast. Like actually fast. Low latency, massive 2M context window, strong tool calling, and code outputs that don’t collapse the moment you introduce edge cases. What keeps coming up from builders is reliability. Fewer hallucinations. Better memory across long sessions. It doesn’t fight you. It doesn’t nanny you. It just does the work. Yes, the free trial helped drive initial adoption. But free doesn’t explain retention at this scale. People stayed because it worked better for serious tasks, not toy prompts. The bigger signal is this: when you strip away marketing, guardrail theater, and benchmark gaming, developers reward models that prioritize truth, speed, and usefulness. Source: X Freeze, OpenRouter, Grok
0:30

GROK CODE FAST 1 TAKES #1 ON OPENROUTER, DEVELOPERS PICK REAL PERFORMANCE OVER HYPE Grok Code Fast 1 just locked in the top spot on OpenRouter’s December 2025 monthly leaderboard, and this one actually matters. Real workloads. Real builders choosing what they trust when things break, scale, or need to ship. According to OpenRouter data, Grok Code Fast 1 processed billions of tokens in production, clearing every major competitor. Claude Sonnet 4, GPT-5 variants, Gemini, DeepSeek , all solid models, all left behind. Developers didn’t debate it on X. They just routed traffic. The reasons are practical, not philosophical. Grok Code Fast 1 is fast. Like actually fast. Low latency, massive 2M context window, strong tool calling, and code outputs that don’t collapse the moment you introduce edge cases. What keeps coming up from builders is reliability. Fewer hallucinations. Better memory across long sessions. It doesn’t fight you. It doesn’t nanny you. It just does the work. Yes, the free trial helped drive initial adoption. But free doesn’t explain retention at this scale. People stayed because it worked better for serious tasks, not toy prompts. The bigger signal is this: when you strip away marketing, guardrail theater, and benchmark gaming, developers reward models that prioritize truth, speed, and usefulness. Source: X Freeze, OpenRouter, Grok

Mario Nawfal

39,820 görüntüleme • 7 ay önce

I tried @ReelQuestAI recently, and it honestly feels like turning imagination directly into a playable game. Create your own playable world here: You describe the world, characters, gameplay, story, enemies, quests and even the vibe, AI builds a playable experience from it without needing to code. What normally takes weeks of planning, designing, and prototyping can now happen in minutes. It’s especially useful for creators who want to test ideas fast, experiment with different concepts, or bring cinematic worlds to life without a full dev team. Feels less like a game tool and more like an AI-powered game studio for creators.
0:49

I tried @ReelQuestAI recently, and it honestly feels like turning imagination directly into a playable game. Create your own playable world here: You describe the world, characters, gameplay, story, enemies, quests and even the vibe, AI builds a playable experience from it without needing to code. What normally takes weeks of planning, designing, and prototyping can now happen in minutes. It’s especially useful for creators who want to test ideas fast, experiment with different concepts, or bring cinematic worlds to life without a full dev team. Feels less like a game tool and more like an AI-powered game studio for creators.

Sharon Riley

32,261 görüntüleme • 2 ay önce