Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

LLM + Memory + Planning + Tools = Agents 🤖 Last month, Job and I discussed how generative AI is shifting how companies offer customer support. How can we add more layers to our RAG apps to make it more agentic? LLM: Large language model alone Memory: Short-term and...

eshorten300's profile picture

Erika Shorten

4,798 subscribers

32,443 görüntüleme • 2 yıl önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

11 Yorum

Erika Cardenas profil fotoğrafı
Erika Cardenas2 yıl önce

You can register for the on-demand recording here: 🙂

Clint J. profil fotoğrafı
Clint J.2 yıl önce

Short, Sweet, and Effective. From this small clip someone can build almost anything.

Erika Cardenas profil fotoğrafı
Erika Cardenas2 yıl önce

Thank you, Clint! Each component is powerful, but together is better 🚀

Krish Dasgupta profil fotoğrafı
Krish Dasgupta2 yıl önce

This is awesome ! Erika !

Erika Cardenas profil fotoğrafı
Erika Cardenas2 yıl önce

Thank you, Krish ☺️

Bob van Luijt profil fotoğrafı
Bob van Luijt2 yıl önce

🎶 who lives in a pineapple under the sea? 🎶

Erika Cardenas profil fotoğrafı
Erika Cardenas2 yıl önce

The nostalgia

Science&Technology🖖 profil fotoğrafı
Science&Technology🖖1 yıl önce

This is such an intriguing topic! 🤔💡 Excited to see how LLMs and memory can elevate customer support. Let’s keep innovating! 🚀✨

Connor Shorten profil fotoğrafı
Connor Shorten2 yıl önce

🤖💬🔥

Vaibhav Jindal profil fotoğrafı
Vaibhav Jindal2 yıl önce

Awesome👍

Erika Cardenas profil fotoğrafı
Erika Cardenas2 yıl önce

Thanks!

Benzer Videolar

I'm excited to share my talk on building Agentic RAG systems at last week's event with Arize AI and Google! 🥳 My talk covered: 1. The differences between Vanilla RAG and Agentic RAG 2. The agent ecosystem and how you can build agents today 3. How Weaviate AI Database is building agents with Generative Feedback Loops (GFLs) This snippet presents the multi-agent paradigm for Agentic RAG. I hope you find this talk interesting and would love to know what you think! The slide deck and full video links are below.
2:37

I'm excited to share my talk on building Agentic RAG systems at last week's event with Arize AI and Google! 🥳 My talk covered: 1. The differences between Vanilla RAG and Agentic RAG 2. The agent ecosystem and how you can build agents today 3. How Weaviate AI Database is building agents with Generative Feedback Loops (GFLs) This snippet presents the multi-agent paradigm for Agentic RAG. I hope you find this talk interesting and would love to know what you think! The slide deck and full video links are below.

Erika Shorten

61,515 görüntüleme • 1 yıl önce

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:
2:06

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

Andrew Ng

132,058 görüntüleme • 1 yıl önce

Most robot datasets store one sentence per episode: the task. Real problems need more: a plan, a memory, room to answer questions and change course. We just shipped full language support in the LeRobot dataset format. Now lerobot-annotate points a vision-language model at each episode and writes the subtasks, plans, memory, and grounded Q&A itself - roughly $1.20 for 100 episodes. From there, recipes turn the annotated rows into policy-agnostic training messages, so the same dataset can teach planning, memory, tool calls, or low-level control, no dataset redesign required. Read how it all works on the blog:
0:20

Most robot datasets store one sentence per episode: the task. Real problems need more: a plan, a memory, room to answer questions and change course. We just shipped full language support in the LeRobot dataset format. Now lerobot-annotate points a vision-language model at each episode and writes the subtasks, plans, memory, and grounded Q&A itself - roughly $1.20 for 100 episodes. From there, recipes turn the annotated rows into policy-agnostic training messages, so the same dataset can teach planning, memory, tool calls, or low-level control, no dataset redesign required. Read how it all works on the blog:

LeRobot

13,451 görüntüleme • 2 ay önce

Open sourcing Dynamic Graph Memory by mem0. Memory is fundamental to human reasoning, shaping how we approach tasks and make decisions. At Mem0, we believe that AI agents & apps should reflect this principle. Our Dynamic Graph Memory emulates human memory, advancing AI agents toward more intelligent, human-like reasoning. This is a significant step forward in building AI that truly understands and interacts with the world like we do. All credit to Dev Khant Deshraj Yadav Prateek Chhikara for their countless nights spent on bringing this to life. Link:
0:26

Open sourcing Dynamic Graph Memory by mem0. Memory is fundamental to human reasoning, shaping how we approach tasks and make decisions. At Mem0, we believe that AI agents & apps should reflect this principle. Our Dynamic Graph Memory emulates human memory, advancing AI agents toward more intelligent, human-like reasoning. This is a significant step forward in building AI that truly understands and interacts with the world like we do. All credit to Dev Khant Deshraj Yadav Prateek Chhikara for their countless nights spent on bringing this to life. Link:

Taranjeet

51,129 görüntüleme • 2 yıl 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

201,127 görüntüleme • 1 yıl önce

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.
5:50

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Zeb Evans

320,989 görüntüleme • 9 ay önce

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below
42:43

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below

Lunar

356,086 görüntüleme • 2 ay önce

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m lecture: • 00:00 - understanding the different layers of AI memory • 30:00 - moving from simple LLM calls to AI agents • 50:00 - why agent systems are becoming a graph engineering problem • 1:12:00 - connecting context, tools and agent state • 1:24:00 - building a minimal agent harness from scratch • 1:46:00 - breaking down the architecture behind Hermes Agent • 2:08:00 - turning agent concepts into working systems 167-minute deep dive, and one of the clearest ways to understand how AI engineering is moving beyond prompts The progression: Prompt → Context → Memory → Agent → Loop → Graph → Agent Harness Watch it today, then read the full roadmap below
2:47:42

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m lecture: • 00:00 - understanding the different layers of AI memory • 30:00 - moving from simple LLM calls to AI agents • 50:00 - why agent systems are becoming a graph engineering problem • 1:12:00 - connecting context, tools and agent state • 1:24:00 - building a minimal agent harness from scratch • 1:46:00 - breaking down the architecture behind Hermes Agent • 2:08:00 - turning agent concepts into working systems 167-minute deep dive, and one of the clearest ways to understand how AI engineering is moving beyond prompts The progression: Prompt → Context → Memory → Agent → Loop → Graph → Agent Harness Watch it today, then read the full roadmap below

Morlex

51,952 görüntüleme • 1 ay önce

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!
2:06

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!

Andrew Ng

297,303 görüntüleme • 2 yıl önce

$TSLA Tesla is breaking down… is it time to panic? In this video, I break down my short term and long term view on Tesla, what I’m expecting next, and how I’m planning to play it. We bought Tesla’s exact bottom around $230 last year and sold near $450.Now I’m looking to position for the next bottom and ride it to new ATHs as Tesla finally breaks out of this 5 year base and pushes toward $1000.
13:52

$TSLA Tesla is breaking down… is it time to panic? In this video, I break down my short term and long term view on Tesla, what I’m expecting next, and how I’m planning to play it. We bought Tesla’s exact bottom around $230 last year and sold near $450.Now I’m looking to position for the next bottom and ride it to new ATHs as Tesla finally breaks out of this 5 year base and pushes toward $1000.

The Swing Trader

64,229 görüntüleme • 6 ay önce

🚨 AI agents are starting to feel less like tools and more like actual coworkers? Larry Goldberg breaks down Grok Bot, which can log into apps and actually finish tasks for you - send emails, make reservations, update a CRM, organize files and handle customer support! The interesting part is how simple it feels compared with earlier agent systems. Give it a job, let it work, and get the result back. If this keeps improving, we may eventually stop opening half the apps on our phones. We’ll just tell the agent what we want done. 👀
9:28

🚨 AI agents are starting to feel less like tools and more like actual coworkers? Larry Goldberg breaks down Grok Bot, which can log into apps and actually finish tasks for you - send emails, make reservations, update a CRM, organize files and handle customer support! The interesting part is how simple it feels compared with earlier agent systems. Give it a job, let it work, and get the result back. If this keeps improving, we may eventually stop opening half the apps on our phones. We’ll just tell the agent what we want done. 👀

Herbert Ong

12,131 görüntüleme • 1 ay önce

Hi everyone!! Our first public (beta) release of cardano-init is out! 🥳🎉 This tool creates new projects ready to go; it encodes how Cardano tools fit together, analyzes and helps you set up the environment, and more! We're making it easy to build new Cardano DApps for newcomers and LLM agents alike! 🤖 This is an early beta release; we haven’t integrated all the tools, we can still make a lot of changes, and we have many improvements in the pipeline! Be sure to check out our plan/roadmap (in the repo) and share your thoughts! 💪😄 Check it out here:
1:06

Hi everyone!! Our first public (beta) release of cardano-init is out! 🥳🎉 This tool creates new projects ready to go; it encodes how Cardano tools fit together, analyzes and helps you set up the environment, and more! We're making it easy to build new Cardano DApps for newcomers and LLM agents alike! 🤖 This is an early beta release; we haven’t integrated all the tools, we can still make a lot of changes, and we have many improvements in the pipeline! Be sure to check out our plan/roadmap (in the repo) and share your thoughts! 💪😄 Check it out here:

🪏 Robertino

48,405 görüntüleme • 1 ay önce

researchers gave a tiny local model human-style memory and its context limit basically stopped existing a team from MBZUAI, Princeton and Weizmann took a 1B model and rebuilt how it reads. instead of attending to everything at once, the model reads in 1,024 token chunks and passes the important stuff forward through an associative memory, the same way you carry the plot of a book between chapters without rereading them. the design mirrors human memory on purpose. full attention inside a chunk works as short-term memory. the module that carries information between chunks works as long-term memory. they even trained it like a person, starting with short easy texts and raising the difficulty gradually, because memory thrown into the deep end learns nothing. the numbers back it up. the normal model burns 40GB of GPU memory on a long document and collapses hard past its limit, dropping from 0.86 to 0.32 accuracy. the memory version holds 0.71 at double that length while using a flat 12GB no matter how long the input gets. it also needs about 30% fewer FLOPs. the part i keep thinking about is that nobody scaled anything here. they didn't build a bigger model, didn't stretch the window, didn't add compute. they looked at how a brain handles a long day and copied the architecture. a model small enough to run on a consumer gpu now survives documents its own architecture used to choke on. we keep treating intelligence as a compute problem. sometimes it's a memory problem.
0:43

researchers gave a tiny local model human-style memory and its context limit basically stopped existing a team from MBZUAI, Princeton and Weizmann took a 1B model and rebuilt how it reads. instead of attending to everything at once, the model reads in 1,024 token chunks and passes the important stuff forward through an associative memory, the same way you carry the plot of a book between chapters without rereading them. the design mirrors human memory on purpose. full attention inside a chunk works as short-term memory. the module that carries information between chunks works as long-term memory. they even trained it like a person, starting with short easy texts and raising the difficulty gradually, because memory thrown into the deep end learns nothing. the numbers back it up. the normal model burns 40GB of GPU memory on a long document and collapses hard past its limit, dropping from 0.86 to 0.32 accuracy. the memory version holds 0.71 at double that length while using a flat 12GB no matter how long the input gets. it also needs about 30% fewer FLOPs. the part i keep thinking about is that nobody scaled anything here. they didn't build a bigger model, didn't stretch the window, didn't add compute. they looked at how a brain handles a long day and copied the architecture. a model small enough to run on a consumer gpu now survives documents its own architecture used to choke on. we keep treating intelligence as a compute problem. sometimes it's a memory problem.

Alex Veremeyenko

16,147 görüntüleme • 2 ay önce

STANFORD BUILT AN LLM MEMORY THAT WORKS LIKE A BRAIN AND IT MADE STANDARD RAG LOOK ANCIENT no fine-tuning. no bigger model. just a smarter way to remember the insight: the brain doesn't store memories as isolated notes. it indexes them and links them - so one cue pulls back the whole memory so HippoRAG stops treating documents as separate chunks. it builds a knowledge graph, then spreads activation across it (Personalized PageRank) to pull a full answer from a single cue - the brain calls this "pattern completion" the result: > up to 20% better on hard multi-hop questions > 10-30x cheaper and 6-13x faster than iterative retrieval > connects facts split across documents in a single step most RAG still encodes every passage in isolation - so it breaks the moment the answer is scattered more retrieval was never the answer. brain-like memory is bookmark this. the next leap in AI agents is how they remember, not how big they get
0:29

STANFORD BUILT AN LLM MEMORY THAT WORKS LIKE A BRAIN AND IT MADE STANDARD RAG LOOK ANCIENT no fine-tuning. no bigger model. just a smarter way to remember the insight: the brain doesn't store memories as isolated notes. it indexes them and links them - so one cue pulls back the whole memory so HippoRAG stops treating documents as separate chunks. it builds a knowledge graph, then spreads activation across it (Personalized PageRank) to pull a full answer from a single cue - the brain calls this "pattern completion" the result: > up to 20% better on hard multi-hop questions > 10-30x cheaper and 6-13x faster than iterative retrieval > connects facts split across documents in a single step most RAG still encodes every passage in isolation - so it breaks the moment the answer is scattered more retrieval was never the answer. brain-like memory is bookmark this. the next leap in AI agents is how they remember, not how big they get

NO1ennn

32,454 görüntüleme • 1 ay önce

This is the most complete setup I've seen yet to turn Claude Code into your personal OS. Here's my new episode with Moritz Kremb where he shared the system that runs his email, content, and even grocery shopping. We talked about: → The 4 layers: folders, tools, skills, routines → Memory: Set up a nightly "dreaming" job → Tools: The best CLIs and MCPs to use → Skills: Video edits, planning, and more → Routines: When to use local vs. remote 📌 Watch now: Thanks to our sponsors: Wispr Flow: Don't type, just speak Linear: The AI agent platform for modern teams
0:36

This is the most complete setup I've seen yet to turn Claude Code into your personal OS. Here's my new episode with Moritz Kremb where he shared the system that runs his email, content, and even grocery shopping. We talked about: → The 4 layers: folders, tools, skills, routines → Memory: Set up a nightly "dreaming" job → Tools: The best CLIs and MCPs to use → Skills: Video edits, planning, and more → Routines: When to use local vs. remote 📌 Watch now: Thanks to our sponsors: Wispr Flow: Don't type, just speak Linear: The AI agent platform for modern teams

Peter Yang

113,939 görüntüleme • 4 ay önce

arXiv Papers → LLM Artifacts This is how I keep up with AI research now. It's like having access to the most personalized arXiv feed. Automations run everyday to curate papers based a set of rules and insights. Curated papers are indexed and power the artifacts. Agent convert papers to LLM wikis (based on Andrej Karpathy idea), which means insights are indexed and easily searchable and reusable. I feel like LLM Artifacts is the natural evolution to LLM Wikis. It's about making that knowledge actionable. Artifacts are customizable via agents. Artifacts can interact with agents and are dynamic in nature. Anything can be injected into the artifact as needed (insights, components, suggested experiments, action items, etc). I can take action on Artifact items with my agent orchestrator (Electron app). So I can ask questions about any paper and automate experiments in the background right from within the artifact. This is more than a visual. It's not a single prompt. It's several proactive agents coordinating to surface interesting facts, knowledge, and insights that I can act on a researcher. Agents are not just for generating useful artifacts, they are useful to keep learning and staying on the cutting edge of knowledge. Stay tuned for more.
0:20

arXiv Papers → LLM Artifacts This is how I keep up with AI research now. It's like having access to the most personalized arXiv feed. Automations run everyday to curate papers based a set of rules and insights. Curated papers are indexed and power the artifacts. Agent convert papers to LLM wikis (based on Andrej Karpathy idea), which means insights are indexed and easily searchable and reusable. I feel like LLM Artifacts is the natural evolution to LLM Wikis. It's about making that knowledge actionable. Artifacts are customizable via agents. Artifacts can interact with agents and are dynamic in nature. Anything can be injected into the artifact as needed (insights, components, suggested experiments, action items, etc). I can take action on Artifact items with my agent orchestrator (Electron app). So I can ask questions about any paper and automate experiments in the background right from within the artifact. This is more than a visual. It's not a single prompt. It's several proactive agents coordinating to surface interesting facts, knowledge, and insights that I can act on a researcher. Agents are not just for generating useful artifacts, they are useful to keep learning and staying on the cutting edge of knowledge. Stay tuned for more.

elvis

59,673 görüntüleme • 4 ay önce

I built an agent that answers machine-learning questions. It's autonomous, and the best part is that I built the whole thing without writing a single line of Python code. Here is what I did and how I did it: Over a year ago, a friend and I built a site that publishes multi-choice questions. You get a new one every day. I decided to have GPT-3.5 answer questions. Here is what I needed to build: 1. Connect to the site's API to retrieve today's question 2. Extract the question and the potential choices 3. Connect to OpenAI's API and ask GPT-3.5 to answer the question 4. Parse the answer from the model 5. Submit the answer back to the API to get the score Not difficult. Likely several hours of work. But I didn't have to write any code. I built the whole thing by dragging and dropping components using Vellum is a YC-backed platform for developers to build LLM applications. They are the only ones I've seen offering this functionality. They sponsored this post, and their team helped me with all my questions while I built this. I created a workflow. The platform supports several node types to build whatever you have in mind. I show how I put the whole thing together in the attached video. The only code I had to write was a few lines of Jinja to parse and transform the API and the LLM results. There are three lessons I want to share from this experience: First, the best possible code is the one you didn't write. I'm a big fan of no-code tools because they help me materialize my ideas fast. They help product people, designers, and no coders collaborate on the solution. Second, Large Language Models are sensitive to how you prompt them. Small changes to prompts can make a big difference in results. This is more pronounced when you are building a multi-step workflow. Third, automated testing and evaluation for prompts is critical. There aren't many companies thinking about this. They'll have a hard time moving from a demo phase. The attached video will show you what I did.
3:46

I built an agent that answers machine-learning questions. It's autonomous, and the best part is that I built the whole thing without writing a single line of Python code. Here is what I did and how I did it: Over a year ago, a friend and I built a site that publishes multi-choice questions. You get a new one every day. I decided to have GPT-3.5 answer questions. Here is what I needed to build: 1. Connect to the site's API to retrieve today's question 2. Extract the question and the potential choices 3. Connect to OpenAI's API and ask GPT-3.5 to answer the question 4. Parse the answer from the model 5. Submit the answer back to the API to get the score Not difficult. Likely several hours of work. But I didn't have to write any code. I built the whole thing by dragging and dropping components using Vellum is a YC-backed platform for developers to build LLM applications. They are the only ones I've seen offering this functionality. They sponsored this post, and their team helped me with all my questions while I built this. I created a workflow. The platform supports several node types to build whatever you have in mind. I show how I put the whole thing together in the attached video. The only code I had to write was a few lines of Jinja to parse and transform the API and the LLM results. There are three lessons I want to share from this experience: First, the best possible code is the one you didn't write. I'm a big fan of no-code tools because they help me materialize my ideas fast. They help product people, designers, and no coders collaborate on the solution. Second, Large Language Models are sensitive to how you prompt them. Small changes to prompts can make a big difference in results. This is more pronounced when you are building a multi-step workflow. Third, automated testing and evaluation for prompts is critical. There aren't many companies thinking about this. They'll have a hard time moving from a demo phase. The attached video will show you what I did.

Santiago

309,825 görüntüleme • 3 yıl önce

Qwen3.8-Flash-Next is still going strong at 364.7K tokens of context on an M5 Max. And this isn’t just a static long-context test. The model was reasoning about how to speed up its own workflow while using tools, and the tool calls kept working without misses. Setup: • Qwen3.8-Flash-Next • M5 Max • 128GB unified memory • MLX-Serve PR #363 • OpenCode 2 • 364.7K context The interesting part isn’t simply getting hundreds of thousands of tokens into memory. It’s what happens once the context gets this large. Long-context inference usually comes with a painful tradeoff. As the KV cache grows, memory pressure increases and generation can slow down. But this setup is still pushing through 364K tokens while maintaining a usable agent workflow. The model can reason, call tools, inspect results, continue working, and keep the session moving. And the tool calls reportedly haven’t missed so far. That’s important for agentic coding. A huge context window is only useful if the model can actually operate reliably inside it. A 400K-token context that constantly breaks tool calls isn’t very useful. A 364K session that can keep reasoning and executing tools is a different story. And the test isn’t finished yet. The current run is approaching 400K tokens, with the expectation that it can keep going. This is also another interesting example of why Apple Silicon keeps showing up in local LLM experiments. The M5 Max’s unified memory gives a large model and its growing KV cache access to one shared memory pool. With MLX-Serve continuing to improve, these machines are becoming surprisingly capable long-context inference boxes. The bigger takeaway: Context length is becoming a workload, not just a model specification. Running a model at 256K is one thing. Keeping an agent alive at 300K+ while it reasons and uses tools is much more interesting. And Qwen3.8-Flash-Next is showing that this can be pushed surprisingly far on a single 128GB Mac. 364.7K and counting. Next stop: 400K.
0:33

Qwen3.8-Flash-Next is still going strong at 364.7K tokens of context on an M5 Max. And this isn’t just a static long-context test. The model was reasoning about how to speed up its own workflow while using tools, and the tool calls kept working without misses. Setup: • Qwen3.8-Flash-Next • M5 Max • 128GB unified memory • MLX-Serve PR #363 • OpenCode 2 • 364.7K context The interesting part isn’t simply getting hundreds of thousands of tokens into memory. It’s what happens once the context gets this large. Long-context inference usually comes with a painful tradeoff. As the KV cache grows, memory pressure increases and generation can slow down. But this setup is still pushing through 364K tokens while maintaining a usable agent workflow. The model can reason, call tools, inspect results, continue working, and keep the session moving. And the tool calls reportedly haven’t missed so far. That’s important for agentic coding. A huge context window is only useful if the model can actually operate reliably inside it. A 400K-token context that constantly breaks tool calls isn’t very useful. A 364K session that can keep reasoning and executing tools is a different story. And the test isn’t finished yet. The current run is approaching 400K tokens, with the expectation that it can keep going. This is also another interesting example of why Apple Silicon keeps showing up in local LLM experiments. The M5 Max’s unified memory gives a large model and its growing KV cache access to one shared memory pool. With MLX-Serve continuing to improve, these machines are becoming surprisingly capable long-context inference boxes. The bigger takeaway: Context length is becoming a workload, not just a model specification. Running a model at 256K is one thing. Keeping an agent alive at 300K+ while it reasons and uses tools is much more interesting. And Qwen3.8-Flash-Next is showing that this can be pushed surprisingly far on a single 128GB Mac. 364.7K and counting. Next stop: 400K.

FHILY👑

39,982 görüntüleme • 25 gün önce

🚨 YOUR GPU IS PROBABLY WASTING MORE THAN YOU THINK. vLLM is built to squeeze far more useful work out of your GPU when serving LLMs. Running an LLM at scale isn’t just about having a powerful GPU. The real problem is how efficiently you use its memory and compute. That’s where vLLM comes in. → High-throughput LLM inference and serving → PagedAttention for smarter KV-cache memory management → Continuous batching to keep GPUs busy → Prefix caching + chunked prefill → OpenAI-compatible API out of the box → Supports a huge range of modern LLM architectures → Quantization support for running models more efficiently And the crazy part? You can start an OpenAI-compatible inference server with: `vllm serve ` So your application can talk to your own model almost like it’s talking to OpenAI. The bigger idea: Don’t just buy more GPUs. Make the GPUs you already have work harder. That’s why vLLM has become such a major project in LLM inference. 🔥 #vLLM #AI #LLM #Inference #GPU #MachineLearning #AIInfrastructure #OpenSource #AIAgents #Developers
0:20

🚨 YOUR GPU IS PROBABLY WASTING MORE THAN YOU THINK. vLLM is built to squeeze far more useful work out of your GPU when serving LLMs. Running an LLM at scale isn’t just about having a powerful GPU. The real problem is how efficiently you use its memory and compute. That’s where vLLM comes in. → High-throughput LLM inference and serving → PagedAttention for smarter KV-cache memory management → Continuous batching to keep GPUs busy → Prefix caching + chunked prefill → OpenAI-compatible API out of the box → Supports a huge range of modern LLM architectures → Quantization support for running models more efficiently And the crazy part? You can start an OpenAI-compatible inference server with: `vllm serve ` So your application can talk to your own model almost like it’s talking to OpenAI. The bigger idea: Don’t just buy more GPUs. Make the GPUs you already have work harder. That’s why vLLM has become such a major project in LLM inference. 🔥 #vLLM #AI #LLM #Inference #GPU #MachineLearning #AIInfrastructure #OpenSource #AIAgents #Developers

Vikas gupta

14,138 görüntüleme • 21 gün önce

“Perform with Dr. Andy Galpin” is back! A new episode is out today, with new episodes releasing every Wednesday. In today’s episode, I share science-backed tools for boosting metabolism and maintaining sustainable fat loss. I break down the key components of total daily energy expenditure (TDEE) and explain why some people seem to stay naturally lean with little effort. I also cover how to assess your metabolism and strategies to boost it in both the short and long term using behavioral tools, nutrition, exercise, supplements, and more. If you have questions or comments, drop them in the comments section below—I’d love to hear from you.
1:29

“Perform with Dr. Andy Galpin” is back! A new episode is out today, with new episodes releasing every Wednesday. In today’s episode, I share science-backed tools for boosting metabolism and maintaining sustainable fat loss. I break down the key components of total daily energy expenditure (TDEE) and explain why some people seem to stay naturally lean with little effort. I also cover how to assess your metabolism and strategies to boost it in both the short and long term using behavioral tools, nutrition, exercise, supplements, and more. If you have questions or comments, drop them in the comments section below—I’d love to hear from you.

Andy Galpin, PhD

68,684 görüntüleme • 1 yıl önce