Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Introducing an open source implementation of Cognition's dreaming memory system, same as Instinct, Muse, Openclaw, etc., built on Cloudflare Artifacts, Durable objects, Alchemy and Effect. I've been exploring agent memory for a long time and this is one of the more popular ways to do it, and I'm happy... to see cognition putting out a detailed spec of how they perceive this. In a way, it's beautifully simple and encapsulates what a good memory system should have. There's many pros and cons, here's a video of me talking about it ↓ If you're thinking about agent memory you should probably use supermemory - we think a lot about the very specific details about all of this. But, if you're curious, is a great place to start with the cognition memory thing as well. we're actually going to incorporate some of the learnings from the research we're doing here into supermemory (soon-ish). but open sourcing it for public benefit :) sorry for the bad audio quality, did it as a quick thingshow more

Dhravya Shah

64,655 subscribers

54,724 görüntüleme • 11 gün önce •via X (Twitter)

Eğitim Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

12 Yorum

freyz profil fotoğrafı

freyz11 gün önce

@Cloudflare hey it would be interesting hear your opinion on @VictorTaelin optchat

Dhravya Shah profil fotoğrafı

Dhravya Shah11 gün önce

Github here -

Vishal Anton profil fotoğrafı

Vishal Anton11 gün önce

@Cloudflare bookmarking this for the weekend.

Alek profil fotoğrafı

Alek11 gün önce

the api quickstart drops .user when it saves .token, but its next request still uses /api/users/ada/chat. keep both fields from /auth/verify and put the returned user id in that url. auth.ts adds a hash to ada, and the session check matches the full id.

Hari profil fotoğrafı

Hari11 gün önce

@Cloudflare ive been playing w graphs for a couple weeks this is cool im gonna try

Dhravya Shah profil fotoğrafı

Dhravya Shah11 gün önce

@Cloudflare This is not really a graph, it's just things pointing to each other in a way, quite simple, like obsidian

Hari profil fotoğrafı

Hari11 gün önce

@Cloudflare my method was postgres storing graph nodes, node = *file object in wasm sandbox and agent gets python repl that can also run in wasmruntime (no other tools except this) (for personal agent)

why profil fotoğrafı

why11 gün önce

@Cloudflare The Durable Objects + Artifacts stack seems like a neat fit for persistent agent memory. Curious how you handle memory retrieval across sessions.

thoriq profil fotoğrafı

thoriq11 gün önce

@Cloudflare he's at it agian

Dhravya Shah profil fotoğrafı

Dhravya Shah11 gün önce

@Cloudflare I am always at it

Huy Nguyen profil fotoğrafı

Huy Nguyen10 gün önce

@Cloudflare A morning changelog would make the dreaming part easier to trust: what was removed, what was combined, and what new assumption was added. Then you can catch a bad inference before it affects the next session.

Shyam Toprani profil fotoğrafı

Shyam Toprani10 gün önce

@Cloudflare How does it compare to optMem and optChat?

Benzer Videolar

OpenClaw's memory out of the box sucks With this simple Obsidian system, it's actually awesome In this video I go over using Obsidian as a memory layer for your AI agent, making it SO much more smarter than it is now If you use OpenClaw or Hermes, you need to watch this:

OpenClaw's memory out of the box sucks With this simple Obsidian system, it's actually awesome In this video I go over using Obsidian as a memory layer for your AI agent, making it SO much more smarter than it is now If you use OpenClaw or Hermes, you need to watch this:

Alex Finn

89,897 görüntüleme • 6 ay önce

Ben Thompson says the memory makers are Iran, and by making the Strait of Hormuz mistake are inviting the whole industry to build around them "The other thing, the risk they run, is Apple. Apple's lobbying to get Chinese memory, right?" "And what is the number one focus of algorithmic changes? How can we use less memory?" "I think the memory makers probably screw themselves in the long run by creating such a massive target on their back." "I've analogized memory makers to Iran. The issue with the Strait of Hormuz is it's very effective. It's more effective if you don't use it, cuz then it's always hanging out there as something you could do. Now they did it. Turns out it worked." "But the UAE and Saudi Arabia, they're going to build pipelines. They're going to build new ports. They're not going to let this happen again." "It's very painful right now. But say Iran wants to close the Strait of Hormuz in 2035. It's not going to have any effect, because it will have been built around." "My concern for the memory makers is they might have done the same thing. No one's going to let themselves get in this situation again as far as memory goes."

Ben Thompson says the memory makers are Iran, and by making the Strait of Hormuz mistake are inviting the whole industry to build around them "The other thing, the risk they run, is Apple. Apple's lobbying to get Chinese memory, right?" "And what is the number one focus of algorithmic changes? How can we use less memory?" "I think the memory makers probably screw themselves in the long run by creating such a massive target on their back." "I've analogized memory makers to Iran. The issue with the Strait of Hormuz is it's very effective. It's more effective if you don't use it, cuz then it's always hanging out there as something you could do. Now they did it. Turns out it worked." "But the UAE and Saudi Arabia, they're going to build pipelines. They're going to build new ports. They're not going to let this happen again." "It's very painful right now. But say Iran wants to close the Strait of Hormuz in 2035. It's not going to have any effect, because it will have been built around." "My concern for the memory makers is they might have done the same thing. No one's going to let themselves get in this situation again as far as memory goes."

Fireside Alpha

205,967 görüntüleme • 2 ay 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:

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

132,225 görüntüleme • 1 yıl önce

Career update: i'm joining supermemory to lead Dev GTM. supermemory is the memory layer for AI products, we got the best public results on AI memory by a wide margin, 95% on the leading benchmarks. my role will be to make it easy for everyone to use. demos, walkthroughs, educational content, and the cleanest possible path from "i need memory in my agent" to shipping. pumped to be working with the coolest team oh, and the team just shipped supermemory local. fully self-contained, open source, runs on any machine in a minute!!

Career update: i'm joining supermemory to lead Dev GTM. supermemory is the memory layer for AI products, we got the best public results on AI memory by a wide margin, 95% on the leading benchmarks. my role will be to make it easy for everyone to use. demos, walkthroughs, educational content, and the cleanest possible path from "i need memory in my agent" to shipping. pumped to be working with the coolest team oh, and the team just shipped supermemory local. fully self-contained, open source, runs on any machine in a minute!!

Muskan Jain

113,703 görüntüleme • 4 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!

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

80 years since the liberation of Auschwitz is a long stretch of time. A lot has changed. But what won’t change is our memory – how that war started, who was guilty, and who did the killing. And we will never forgive. We also remember that thanks to unity and determination, life won in the end. This is how it should always be. Thank you to everyone who keeps and shares the truth about that horrific time. Eternal memory to all the victims of the Holocaust! And thank you everyone who defends life today. It’s time for Europe to become a place without war. We dream about it. And we’re working for it.

80 years since the liberation of Auschwitz is a long stretch of time. A lot has changed. But what won’t change is our memory – how that war started, who was guilty, and who did the killing. And we will never forgive. We also remember that thanks to unity and determination, life won in the end. This is how it should always be. Thank you to everyone who keeps and shares the truth about that horrific time. Eternal memory to all the victims of the Holocaust! And thank you everyone who defends life today. It’s time for Europe to become a place without war. We dream about it. And we’re working for it.

Volodymyr Zelenskyy / Володимир Зеленський

302,257 görüntüleme • 1 yıl önce

SK Hynix's Hoshik Kim admits high bandwidth memory "is not the answer" to the memory-wall problem, and SK is working on different solutions to solve the bottleneck. "No, actually, I kind of agree with Pat. So HBM is not the answer." [SK Hynix is admitting that HBM is a bad memory?] "Nothing is a bad memory. It's a good memory, but it's not the final answer. So actually, HBM will not solve the memory-wall problem. Memory-wall problem is an inherent AI problem, which you cannot avoid." "So we try our best to provide higher bandwidth with this memory, with HBM technology even though it has some limitation, as Pat already mentioned, with thermal, IOs, cost, a lot of stuff. "But that's the only thing we got right now to help ease this memory-wall problem, memory-bottleneck problem. But at the same time, we are working in different directions to solve this memory-wall problem with different solutions."

SK Hynix's Hoshik Kim admits high bandwidth memory "is not the answer" to the memory-wall problem, and SK is working on different solutions to solve the bottleneck. "No, actually, I kind of agree with Pat. So HBM is not the answer." [SK Hynix is admitting that HBM is a bad memory?] "Nothing is a bad memory. It's a good memory, but it's not the final answer. So actually, HBM will not solve the memory-wall problem. Memory-wall problem is an inherent AI problem, which you cannot avoid." "So we try our best to provide higher bandwidth with this memory, with HBM technology even though it has some limitation, as Pat already mentioned, with thermal, IOs, cost, a lot of stuff. "But that's the only thing we got right now to help ease this memory-wall problem, memory-bottleneck problem. But at the same time, we are working in different directions to solve this memory-wall problem with different solutions."

Fireside Alpha

161,722 görüntüleme • 2 ay önce

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!

supermemory

17,235 görüntüleme • 3 ay önce

Ben Thompson uses the Strait of Hormuz to explain why memory makers squeezing the market now guarantees they lose their leverage later: "I think the memory makers probably screw themselves in the long run by creating such a massive target on their back. The issue with the Strait of Hormuz is that it's very effective if you don't use it. Then it's always hanging out there as something you could do. Now they did, and it turns out it worked. But the UAE and Saudi Arabia, they're going to build pipelines, they're going to build new ports. They're not going to let this happen again. So it's very painful right now, but say Iran wants to close the Strait of Hormuz in 2035. It's not going to have any effect, because it will have been built around. My concern for the memory makers is they might have done the same thing. No one is going to let themselves get in this situation again."

Ben Thompson uses the Strait of Hormuz to explain why memory makers squeezing the market now guarantees they lose their leverage later: "I think the memory makers probably screw themselves in the long run by creating such a massive target on their back. The issue with the Strait of Hormuz is that it's very effective if you don't use it. Then it's always hanging out there as something you could do. Now they did, and it turns out it worked. But the UAE and Saudi Arabia, they're going to build pipelines, they're going to build new ports. They're not going to let this happen again. So it's very painful right now, but say Iran wants to close the Strait of Hormuz in 2035. It's not going to have any effect, because it will have been built around. My concern for the memory makers is they might have done the same thing. No one is going to let themselves get in this situation again."

Invest Like the Best

21,582 görüntüleme • 2 ay önce

$SNDK CEO David Goeckeler says inference is a memory-bound problem and HBF could break through some bottlenecks, so it's an enormous opportunity as inference scales, which they'll talk more at their analyst day next week. "Look, there's a ton of innovation going on right now in inference memory architectures, which we think is fantastic, very healthy." "There's a lot of different ideas. We're going to dive into this a little deeper next week at our analyst day…" "But yes, all these are opportunities for us. We think especially inference is a memory-bound problem. Storage is extraordinarily important to the equation." "We showed some stuff in our FMS keynote just a couple of hours ago about how, when you use HBF, we simulate performance and maybe break through some bottlenecks…" "As we scale inference, we think it provides an enormous opportunity. The way we're thinking about this is staying very close to our customers, because they're going to be the ones that define what the architecture is in the future."

$SNDK CEO David Goeckeler says inference is a memory-bound problem and HBF could break through some bottlenecks, so it's an enormous opportunity as inference scales, which they'll talk more at their analyst day next week. "Look, there's a ton of innovation going on right now in inference memory architectures, which we think is fantastic, very healthy." "There's a lot of different ideas. We're going to dive into this a little deeper next week at our analyst day…" "But yes, all these are opportunities for us. We think especially inference is a memory-bound problem. Storage is extraordinarily important to the equation." "We showed some stuff in our FMS keynote just a couple of hours ago about how, when you use HBF, we simulate performance and maybe break through some bottlenecks…" "As we scale inference, we think it provides an enormous opportunity. The way we're thinking about this is staying very close to our customers, because they're going to be the ones that define what the architecture is in the future."

Fireside Alpha

22,024 görüntüleme • 2 ay önce

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

162,636 görüntüleme • 7 ay önce

Nick talks about the Sneako collab and pushes back on some of the criticism he's getting. "We have to have a longer memory for the good things that people do for us as much as we have a memory for the ways that people screw us over."

Nick talks about the Sneako collab and pushes back on some of the criticism he's getting. "We have to have a longer memory for the good things that people do for us as much as we have a memory for the ways that people screw us over."

Fuentes Updates

50,709 görüntüleme • 1 yıl önce

A new way of working. And a scary one at that. Memory Store is one of a group of new kinds of AI-first companies that can turn you into a Fast Company. I’m using several of them on my desktop and they are a dramatically new way to work. It builds a memory for: 1. Your AI agents. 2. Any employee using it. 3. The company itself. I sit down with founder Diwank Singh Tomer, Diwank Singh Tomer, who both freaks me out as well as shows how AI can radically help workers as well as managers. First, why does it freak me out? Well, his AI watches nearly everything a worker does and keeps a “memory” of it. It watches your email. Your calendar. Your Slack. And a whole lot of other things. This can really freak out workers if “forced” on them. And leads to a whole new set of security issues companies need to consider before adopting these things. Such data about a company could give a competitor a HUGE advantage, if leaked. They would know how a company “thinks.” It really is a surveillance system for employees and the company itself. OK, now why would anyone ever use such a thing? Because it gives employees super powers. It makes them more productive. Shows workers a lot of things about themselves, and helps them work and stay on task. It also gives the company super powers. Institutional memory stays with the AI now, even if an employee dies or leaves. As companies move to “AI First” approaches, they will increasingly see the value in companies like Memory Store. It prepares employees for meetings. It helps them remember things. It shows them what they should be working on, and helps them do it. Memory Store builds a memory for: 1. Your agents. 2. Your company. 3. Yourself, or any employee on it. This helps all three work better together. Diwank Singh Tomer and I go in depth about what it does and how deeply it improves working at a company that deploys it. But to get the ultimate benefits you gotta convince your coworkers to use it. And your managers to approve it. Which means you have to get over your fears and get everyone you work with over theirs too. Which will be the challenge for Diwank. Luckily for him his first customers are raving about how good it is and how much his platform helped their companies. Increases sales. Makes teams more productive. Decreases errors and unnecessary costs. Which tells me everyone soon will be using systems like this. This is what the new way of working looks like. Once I got over my fears it sure is an amazing way to work. Will you try working this way?

A new way of working. And a scary one at that. Memory Store is one of a group of new kinds of AI-first companies that can turn you into a Fast Company. I’m using several of them on my desktop and they are a dramatically new way to work. It builds a memory for: 1. Your AI agents. 2. Any employee using it. 3. The company itself. I sit down with founder Diwank Singh Tomer, Diwank Singh Tomer, who both freaks me out as well as shows how AI can radically help workers as well as managers. First, why does it freak me out? Well, his AI watches nearly everything a worker does and keeps a “memory” of it. It watches your email. Your calendar. Your Slack. And a whole lot of other things. This can really freak out workers if “forced” on them. And leads to a whole new set of security issues companies need to consider before adopting these things. Such data about a company could give a competitor a HUGE advantage, if leaked. They would know how a company “thinks.” It really is a surveillance system for employees and the company itself. OK, now why would anyone ever use such a thing? Because it gives employees super powers. It makes them more productive. Shows workers a lot of things about themselves, and helps them work and stay on task. It also gives the company super powers. Institutional memory stays with the AI now, even if an employee dies or leaves. As companies move to “AI First” approaches, they will increasingly see the value in companies like Memory Store. It prepares employees for meetings. It helps them remember things. It shows them what they should be working on, and helps them do it. Memory Store builds a memory for: 1. Your agents. 2. Your company. 3. Yourself, or any employee on it. This helps all three work better together. Diwank Singh Tomer and I go in depth about what it does and how deeply it improves working at a company that deploys it. But to get the ultimate benefits you gotta convince your coworkers to use it. And your managers to approve it. Which means you have to get over your fears and get everyone you work with over theirs too. Which will be the challenge for Diwank. Luckily for him his first customers are raving about how good it is and how much his platform helped their companies. Increases sales. Makes teams more productive. Decreases errors and unnecessary costs. Which tells me everyone soon will be using systems like this. This is what the new way of working looks like. Once I got over my fears it sure is an amazing way to work. Will you try working this way?

Robert Scoble

26,186 görüntüleme • 5 ay önce

"This is how we talk about race in this country. We do a lot of categorical denunciations. For a very long time, it was all about black lives and whiteness and what whiteness does. No one should be shocked that this is how we're talking about Somalians in this context as well."

"This is how we talk about race in this country. We do a lot of categorical denunciations. For a very long time, it was all about black lives and whiteness and what whiteness does. No one should be shocked that this is how we're talking about Somalians in this context as well."

Thomas Hern

84,208 görüntüleme • 10 ay önce

Why the memory layer will become more and more important and how Instinct crushed it “One thing about agents that is rare today but will be incredibly common in the next few years is this memory layer. If you look at Instinct or Muse, one of the things that they have nailed is personalization and learning, making it seem like it is something for you. I think memory is super, super early.” Harrison Chase Love to hear your thoughts Dhravya Shah Taranjeet Noah Shinn Nat Friedman

Why the memory layer will become more and more important and how Instinct crushed it “One thing about agents that is rare today but will be incredibly common in the next few years is this memory layer. If you look at Instinct or Muse, one of the things that they have nailed is personalization and learning, making it seem like it is something for you. I think memory is super, super early.” Harrison Chase Love to hear your thoughts Dhravya Shah Taranjeet Noah Shinn Nat Friedman

Harry Stebbings

30,428 görüntüleme • 1 gün önce

Happy to properly launch Anna, the proactive AI agent for parents! Uncovering a bit of the technology behind the scenes! Building Anna is where I learned: 💾 Memory as plain text sucks. You need structured memory. Like a full-blown PostgreSQL DB that stores your tasks and calendar in a structured manner. Most harnesses are good at coding-related stuff. Let it do the query. Don't let it vibe-search the memory. Let it vibe your SQL query 💭 Dreaming is a useful concept for enhancing memory to feed the LLM context. But DO NOT vibe your dream. Asking your agent to "hey, just dream and keep the relevant memory around" is a recipe for deleting a bunch of important information and keeping trash around. Your dream needs to have some Taxonomy (or better, Ontology). What information is important? For who? With what object? What can they do? And again, these are impossible to describe and act well without a proper schema 🔄 Loop Engineering is important for smoothing out rough edges in the system we build. But even expensive loop engineering with a state-of-the-art model can't out-engineer bad system design. The highest leverage an AI Engineer can do is actually building the right system design, and having an eye on both product delight and engineering scalability There are several more insights that I plan to cover in a dedicated video about Agentic AI Engineering. But it's actually a huge relief that the future of software engineering... is still software engineering

Happy to properly launch Anna, the proactive AI agent for parents! Uncovering a bit of the technology behind the scenes! Building Anna is where I learned: 💾 Memory as plain text sucks. You need structured memory. Like a full-blown PostgreSQL DB that stores your tasks and calendar in a structured manner. Most harnesses are good at coding-related stuff. Let it do the query. Don't let it vibe-search the memory. Let it vibe your SQL query 💭 Dreaming is a useful concept for enhancing memory to feed the LLM context. But DO NOT vibe your dream. Asking your agent to "hey, just dream and keep the relevant memory around" is a recipe for deleting a bunch of important information and keeping trash around. Your dream needs to have some Taxonomy (or better, Ontology). What information is important? For who? With what object? What can they do? And again, these are impossible to describe and act well without a proper schema 🔄 Loop Engineering is important for smoothing out rough edges in the system we build. But even expensive loop engineering with a state-of-the-art model can't out-engineer bad system design. The highest leverage an AI Engineer can do is actually building the right system design, and having an eye on both product delight and engineering scalability There are several more insights that I plan to cover in a dedicated video about Agentic AI Engineering. But it's actually a huge relief that the future of software engineering... is still software engineering

Gogo | Dota for Toxicity

30,766 görüntüleme • 3 ay önce

Martin Keen from IBM just explained the one thing separating "chatbot users" from $300K AI architects > most people use Claude Opus 4.8 as a temporary tool -> the pros build it a permanent memory it's called the CoALA framework. the 4 layers your agent actually needs: > Working Memory - the context window. fast but resets every session. this is the RAM, not the brain > Semantic Memory - your knowledge base. CLAUDE.md, rules, facts the agent never forgets regardless of session > Procedural Memory - skills. workflows and instructions that load only when a specific task begins > Episodic Memory - past lessons. the agent remembers every bug it fixed yesterday so it doesn't repeat it today if your agent doesn't have all four, it's a fancy autocomplete the 2026 job market isn't looking for prompt engineers > it's looking for people who can build AI brains - and the ones doing it now aren't waiting for job postings save this or watch someone else use it to get your next raise 👇

Martin Keen from IBM just explained the one thing separating "chatbot users" from $300K AI architects > most people use Claude Opus 4.8 as a temporary tool -> the pros build it a permanent memory it's called the CoALA framework. the 4 layers your agent actually needs: > Working Memory - the context window. fast but resets every session. this is the RAM, not the brain > Semantic Memory - your knowledge base. CLAUDE.md, rules, facts the agent never forgets regardless of session > Procedural Memory - skills. workflows and instructions that load only when a specific task begins > Episodic Memory - past lessons. the agent remembers every bug it fixed yesterday so it doesn't repeat it today if your agent doesn't have all four, it's a fancy autocomplete the 2026 job market isn't looking for prompt engineers > it's looking for people who can build AI brains - and the ones doing it now aren't waiting for job postings save this or watch someone else use it to get your next raise 👇

Mr. Buzzoni

10,442 görüntüleme • 4 ay önce

Plenty to be proud about 🤘 "We all hope and wish that the that the playoff thing would work...But if it doesn't, there's still a lot to be proud of and a lot of, a lot of great accomplishments, not only from a team perspective, but but some individuals on this team as well"

Plenty to be proud about 🤘 "We all hope and wish that the that the playoff thing would work...But if it doesn't, there's still a lot to be proud of and a lot of, a lot of great accomplishments, not only from a team perspective, but but some individuals on this team as well"

Nash

24,408 görüntüleme • 10 ay önce

Autonomous AI agents can’t afford a memory problem. After OpenClaw, insane numbers of autonomous agents are coming online, but all of them have a memory layer that's breaking. I have been playing around with SureThing these days. It is an autonomous AI agent designed with a native memory layer. → it learns your patterns → integrates with 1000+ apps → fully autonomous They actually benchmarked memory depth. SureThing: 84.8, ChatGPT: 40, OpenClaw: 60. The gap speaks for itself. SureThing is invitation-only. The crazy part is that you have to talk to SureThing agent itself to get the invite code. The onboarding is the product demo. You feel the memory and judgment before you even have an account. Try it here: Partnered with SureThing for this post. Thanks to the team for the support.

Autonomous AI agents can’t afford a memory problem. After OpenClaw, insane numbers of autonomous agents are coming online, but all of them have a memory layer that's breaking. I have been playing around with SureThing these days. It is an autonomous AI agent designed with a native memory layer. → it learns your patterns → integrates with 1000+ apps → fully autonomous They actually benchmarked memory depth. SureThing: 84.8, ChatGPT: 40, OpenClaw: 60. The gap speaks for itself. SureThing is invitation-only. The crazy part is that you have to talk to SureThing agent itself to get the invite code. The onboarding is the product demo. You feel the memory and judgment before you even have an account. Try it here: Partnered with SureThing for this post. Thanks to the team for the support.

Pratham

80,634 görüntüleme • 8 ay önce