Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

1/3 Here's John Sweller talking about how transferring information from working memory to long-term memory transforms us. It's what makes education transformational. Such a fantastic person to have a conversation with. Link to full episode below.

Anna Stokke

8,592 subscribers

17,076 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

We’ve developed a memory system for our models that provides both short-term visual memory and long-term semantic memory. Our approach allows us to train robots to perform long and complex tasks, like cleaning up a kitchen or preparing a grilled cheese sandwich from scratch 👇

We’ve developed a memory system for our models that provides both short-term visual memory and long-term semantic memory. Our approach allows us to train robots to perform long and complex tasks, like cleaning up a kitchen or preparing a grilled cheese sandwich from scratch 👇

Physical Intelligence

455,251 views • 5 months ago

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:

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

131,850 views • 1 year ago

A clip from my conversation with Gary Oldman talking about Jackson Lamb. Link to the full podcast in the tweet below or in your pod app.

A clip from my conversation with Gary Oldman talking about Jackson Lamb. Link to the full podcast in the tweet below or in your pod app.

Barbican Station - A Slow Horses Podcast

10,046 views • 1 year ago

We went from being the worst, to the best AI memory system in the world. While being students with ~no prior research experience. .... but, how do we measure "good" vs bad memory? Evals (and vibes!) here's a small video on how we think about memory.

We went from being the worst, to the best AI memory system in the world. While being students with ~no prior research experience. .... but, how do we measure "good" vs bad memory? Evals (and vibes!) here's a small video on how we think about memory.

Dhravya Shah

120,929 views • 7 months ago

Back in 1981 a film was released that lives on today. Escape To Victory. Here's John Colby, West Ham & England talking about working with the greats. Yes I know, it's Michael Caine. It's still real to me! John Smith

Back in 1981 a film was released that lives on today. Escape To Victory. Here's John Colby, West Ham & England talking about working with the greats. Yes I know, it's Michael Caine. It's still real to me! John Smith

Retro Football Network

26,216 views • 5 months ago

🚨What stocks to buy when Market Bounces! 2 Bounces=2 Mega Green Trades Learn How Focus on Hottest Sector Part 1: Bounce Long on Memory Stocks $MU $SNDK How to use MTFs to long Part 1 Day2 Gap Down long on Memory Stocks Make a plan in premarket Take Long $MU $SNDK

🚨What stocks to buy when Market Bounces! 2 Bounces=2 Mega Green Trades Learn How Focus on Hottest Sector Part 1: Bounce Long on Memory Stocks $MU $SNDK How to use MTFs to long Part 1 Day2 Gap Down long on Memory Stocks Make a plan in premarket Take Long $MU $SNDK

Ripster

17,379 views • 4 months ago

Less than 7% of Harvard freshmen major in the humanities. Philosopher Jennifer A. Frey thinks that says a lot about how we've misunderstood what education is for, a true liberal education isn't yoked to a trade, it's the education that makes you free. From our SuperSalon "Can the Humanities Be Saved?" with host Anastasia Berg. Watch the full conversation here →

Less than 7% of Harvard freshmen major in the humanities. Philosopher Jennifer A. Frey thinks that says a lot about how we've misunderstood what education is for, a true liberal education isn't yoked to a trade, it's the education that makes you free. From our SuperSalon "Can the Humanities Be Saved?" with host Anastasia Berg. Watch the full conversation here →

Interintellect 🧭

271,933 views • 3 months ago

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.

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 views • 13 days ago

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!

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 views • 1 year ago

“He's talking about short-term pain for long-term gain..." @MegynKelly urges Americans to give Trump a chance with his tariffs "Liberation Day" plan. Watch below:

“He's talking about short-term pain for long-term gain..." @MegynKelly urges Americans to give Trump a chance with his tariffs "Liberation Day" plan. Watch below:

The Megyn Kelly Show

33,405 views • 1 year ago

Sana talking about how she wants to preserve every moment with the TWICE members like a polaroid. How every moment will feel like a precious memory to return to 3 years from now and the moment she takes the photo she gets emotional, which the members tease her about 🥺😭

Sana talking about how she wants to preserve every moment with the TWICE members like a polaroid. How every moment will feel like a precious memory to return to 3 years from now and the moment she takes the photo she gets emotional, which the members tease her about 🥺😭

minaron

363,525 views • 1 year ago

Announcing... Voice x Memory! We’re unpacking what makes agents listen, respond, and remember, or sometimes forget, and what that means for building better voice systems. We will move towards a world of large LLMs remembering a lot of information to smaller LMs with finite real-time intelligence and infinite memory. Here's a short teaser as we walk down the streets of SF having a chat with @shortkingceo on how we see the future

Announcing... Voice x Memory! We’re unpacking what makes agents listen, respond, and remember, or sometimes forget, and what that means for building better voice systems. We will move towards a world of large LLMs remembering a lot of information to smaller LMs with finite real-time intelligence and infinite memory. Here's a short teaser as we walk down the streets of SF having a chat with @shortkingceo on how we see the future

Sudarshan Kamath

23,452 views • 5 months ago

🚨 The OriginTrail Bounty is UNDERWAY! 🔥 Round 1 is OPEN NOW — 50,000 TRAC Tokens up for grabs! OriginTrail is paying builders 1,000 to 10,000 TRAC Tokens to connect AI agents (ChatGPT, Claude, OpenClaw, Hermes, etc.) to the new Working Memory and Shared Memory layers in DKG v10. Just dropped a clear breakdown video explaining: ✅ - How the 3 memory layers work ✅ - What makes a Flagship integration (10k TRAC) ✅ - Real examples you can actually build ✅ - How to submit your project If you're a developer or agent builder → this is your moment. Watch the full explainer 👇

🚨 The OriginTrail Bounty is UNDERWAY! 🔥 Round 1 is OPEN NOW — 50,000 TRAC Tokens up for grabs! OriginTrail is paying builders 1,000 to 10,000 TRAC Tokens to connect AI agents (ChatGPT, Claude, OpenClaw, Hermes, etc.) to the new Working Memory and Shared Memory layers in DKG v10. Just dropped a clear breakdown video explaining: ✅ - How the 3 memory layers work ✅ - What makes a Flagship integration (10k TRAC) ✅ - Real examples you can actually build ✅ - How to submit your project If you're a developer or agent builder → this is your moment. Watch the full explainer 👇

dkg://TriniZone

39,451 views • 2 months ago

Six-time USA Memory Champion, Nelson Dellis, joins me on this week’s Chasing Life to dispel the notion that bad memory is something you just have to accept, and he explains how we can all construct our own “memory palace” to keep our recall sharp. “‘I have a terrible memory, I’m terrible with names.' This is actually something you can work on.” Full episode here: and wherever you get your podcasts.

Six-time USA Memory Champion, Nelson Dellis, joins me on this week’s Chasing Life to dispel the notion that bad memory is something you just have to accept, and he explains how we can all construct our own “memory palace” to keep our recall sharp. “‘I have a terrible memory, I’m terrible with names.' This is actually something you can work on.” Full episode here: and wherever you get your podcasts.

Dr. Sanjay Gupta

12,878 views • 1 month ago

It's been awesome to watch Clemson Basketball this season. With only 1 player returning from last year's team, they had to start from scratch, and what they have now is a team that is 9-1 in ACC play. What makes them so good? Here's 3 things that I talked about on the ACC Network

It's been awesome to watch Clemson Basketball this season. With only 1 player returning from last year's team, they had to start from scratch, and what they have now is a team that is 9-1 in ACC play. What makes them so good? Here's 3 things that I talked about on the ACC Network

Terrence Oglesby

20,941 views • 6 months ago

Such a fun Notsam Wrestling talking to new Knicks legend DugLust about his favorite wrestling themes and what makes them so important Full conversation is up on YouTube and the Siriusxm app

Such a fun Notsam Wrestling talking to new Knicks legend DugLust about his favorite wrestling themes and what makes them so important Full conversation is up on YouTube and the Siriusxm app

Sam Roberts

13,129 views • 3 months ago

In my chat with Ravid Shwartz Ziv I spoke to how denoising evolved from a "digital janitor" to the heart of modern diffusion models. It's a powerful reminder that breakthroughs, even in practice, often come from long-term foundational work, not just the latest trends. link to episode👇

In my chat with Ravid Shwartz Ziv I spoke to how denoising evolved from a "digital janitor" to the heart of modern diffusion models. It's a powerful reminder that breakthroughs, even in practice, often come from long-term foundational work, not just the latest trends. link to episode👇

Peyman Milanfar

18,774 views • 3 months ago

I want us to have a nationwide conversation around education. I am establishing a National Convention on Education & want to hear from students, teachers, school staff, the public, and other stakeholders about what they want to see our eduction system look like into the future.

I want us to have a nationwide conversation around education. I am establishing a National Convention on Education & want to hear from students, teachers, school staff, the public, and other stakeholders about what they want to see our eduction system look like into the future.

Helen McEntee TD

699,374 views • 1 year ago