Video yükleniyor...

Video Yüklenemedi

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

Ana Sayfaya Dön

Harrison Chase(LangChain CEO) just walked through four ways to give an agent memory. All four assume the model is still holding the right tokens. It isn't. At token 4,096 the cache ran a silent eviction nobody wrote. The user's name was in that batch. First founder to write the... show more

Rohit

23,613 subscribers

108,519 görüntüleme • 3 ay önce •via X (Twitter)

Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

A tricky LLM interview question: You're serving a reasoning model on vLLM, and it keeps running out of GPU memory on long traces. So you add KV cache compression and evict 90% of the cached tokens. VRAM usage stays as is and GPU still runs out of memory. Why? (answer below) Evicting 90% of the KV cache can free almost none of the memory it was using. This sounds counterintuitive, but it follows directly from how production servers store the cache today. The KV cache grows with every token a model generates. Each token appends its key and value vectors across every layer, and nothing is freed while generation continues. This is the dominant memory cost for reasoning models. If a 32K-token CoT caches ~32K tokens of KV vectors, a Qwen3-32B with 4-bit weights will run out-of-memory around 24K tokens on a 24GB GPU. One obvious solution is to keep the important tokens and drop the rest, since attention is sparse enough to allow it. But this does not solve the memory problem yet. The reason is paged attention, which is the memory manager behind vLLM and most production servers. Under the hood, it splits GPU memory into fixed physical blocks, each one holds the KV for about 16 tokens. This block returns to the allocator only when every slot inside it is empty. Since the eviction logic selects tokens by importance, and such tokens are scattered across blocks... ...so despite eviction, almost every block is left with at least some survivor tokens. For instance, if the logic evicts 14k of 16k tokens across 1,000 blocks, most likely every block will still have a token. This means the allocator frees almost nothing. Placing the new tokens into those freed slots is not ideal because it breaks the cache's layout. Say token 16,001 arrives, and it's placed in the slot the 40th token used to hold. The cache now reads position 38, then 16,001, then 41, so the cache is no longer in token order. Attention can still compute the right answer from that, but only if every slot now carries a separate note recording which position it actually holds. This introduces another bookkeeping cost that an in-order layout inherently avoids. So the cache is logically 90% smaller and still physically the same size. Many compression results miss this because they measure on pre-allocated contiguous tensors rather than a paged server. There's another problem. Eviction methods pick which tokens to keep by looking at the attention scores themselves (as expected). But fast attention kernels used in production, like FlashAttention, never save those scores. They compute attention in small pieces and throw the full score grid away as they go, which is also why they're fast. So the exact signal eviction methods need isn't available in memory. The workaround is to fall back to eager attention and build the full matrix, which gives up the speed FlashAttention was there to provide. NVIDIA published a method called TriAttention to solve both these problems. It never needs attention scores. Instead, it scores tokens from the geometry of the model's key and query vectors before RoPE is applied, where those vectors sit in stable clusters. For the memory problem, it runs a compaction pass every 128 decoded tokens. The surviving tokens slide forward to close the holes eviction creates, so whole blocks empty out and return to the allocator while the cache stays in token order. On long reasoning traces, the approach matches full-attention accuracy while decoding 2.5x faster and using 10.7x less KV memory. KV cache compression is a big infrastructure problem. The number that decides whether it works is the count of freed blocks, not the count of evicted tokens. You can find the NVIDIA write-up here: I wrote a first-principles breakdown of how the KV cache works. It walks through why the model stores keys and values at all, why the cache grows with every token, and a comparison of LLM generation speed with and without KV caching. Read it below.

A tricky LLM interview question: You're serving a reasoning model on vLLM, and it keeps running out of GPU memory on long traces. So you add KV cache compression and evict 90% of the cached tokens. VRAM usage stays as is and GPU still runs out of memory. Why? (answer below) Evicting 90% of the KV cache can free almost none of the memory it was using. This sounds counterintuitive, but it follows directly from how production servers store the cache today. The KV cache grows with every token a model generates. Each token appends its key and value vectors across every layer, and nothing is freed while generation continues. This is the dominant memory cost for reasoning models. If a 32K-token CoT caches ~32K tokens of KV vectors, a Qwen3-32B with 4-bit weights will run out-of-memory around 24K tokens on a 24GB GPU. One obvious solution is to keep the important tokens and drop the rest, since attention is sparse enough to allow it. But this does not solve the memory problem yet. The reason is paged attention, which is the memory manager behind vLLM and most production servers. Under the hood, it splits GPU memory into fixed physical blocks, each one holds the KV for about 16 tokens. This block returns to the allocator only when every slot inside it is empty. Since the eviction logic selects tokens by importance, and such tokens are scattered across blocks... ...so despite eviction, almost every block is left with at least some survivor tokens. For instance, if the logic evicts 14k of 16k tokens across 1,000 blocks, most likely every block will still have a token. This means the allocator frees almost nothing. Placing the new tokens into those freed slots is not ideal because it breaks the cache's layout. Say token 16,001 arrives, and it's placed in the slot the 40th token used to hold. The cache now reads position 38, then 16,001, then 41, so the cache is no longer in token order. Attention can still compute the right answer from that, but only if every slot now carries a separate note recording which position it actually holds. This introduces another bookkeeping cost that an in-order layout inherently avoids. So the cache is logically 90% smaller and still physically the same size. Many compression results miss this because they measure on pre-allocated contiguous tensors rather than a paged server. There's another problem. Eviction methods pick which tokens to keep by looking at the attention scores themselves (as expected). But fast attention kernels used in production, like FlashAttention, never save those scores. They compute attention in small pieces and throw the full score grid away as they go, which is also why they're fast. So the exact signal eviction methods need isn't available in memory. The workaround is to fall back to eager attention and build the full matrix, which gives up the speed FlashAttention was there to provide. NVIDIA published a method called TriAttention to solve both these problems. It never needs attention scores. Instead, it scores tokens from the geometry of the model's key and query vectors before RoPE is applied, where those vectors sit in stable clusters. For the memory problem, it runs a compaction pass every 128 decoded tokens. The surviving tokens slide forward to close the holes eviction creates, so whole blocks empty out and return to the allocator while the cache stays in token order. On long reasoning traces, the approach matches full-attention accuracy while decoding 2.5x faster and using 10.7x less KV memory. KV cache compression is a big infrastructure problem. The number that decides whether it works is the count of freed blocks, not the count of evicted tokens. You can find the NVIDIA write-up here: I wrote a first-principles breakdown of how the KV cache works. It walks through why the model stores keys and values at all, why the cache grows with every token, and a comparison of LLM generation speed with and without KV caching. Read it below.

Avi Chawla

270,809 görüntüleme • 1 ay önce

New AI Agentic course! Learn to use LangGraph to build single and multi-agent LLM applications in AI Agents in LangGraph. This short course, taught by LangChain founder Harrison Chase Harrison Chase and Tavily founder @weiss_rotem, shows how to integrate agentic search to enhance an agent's knowledge with query-focused answers in predictable formats. Also learn to implement agentic memory to save state for reasoning and debugging, and see how human-in-the-loop input can guide agents at key junctures. You'll build an agent from scratch, then reconstruct it with LangGraph to thoroughly understand the framework. Finally, you'll build a sophisticated essay-writing agent that incorporates all the learnings from the course. Sign up here!

New AI Agentic course! Learn to use LangGraph to build single and multi-agent LLM applications in AI Agents in LangGraph. This short course, taught by LangChain founder Harrison Chase Harrison Chase and Tavily founder @weiss_rotem, shows how to integrate agentic search to enhance an agent's knowledge with query-focused answers in predictable formats. Also learn to implement agentic memory to save state for reasoning and debugging, and see how human-in-the-loop input can guide agents at key junctures. You'll build an agent from scratch, then reconstruct it with LangGraph to thoroughly understand the framework. Finally, you'll build a sophisticated essay-writing agent that incorporates all the learnings from the course. Sign up here!

Andrew Ng

152,597 görüntüleme • 2 yıl önce

$NVDA CEO Jensen Huang: This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it.

$NVDA CEO Jensen Huang: This is actually an incredible time to be a software company. But the software has to be presented to the agent in a way that the agent can use it.

Wall St Engine

68,076 görüntüleme • 2 ay önce

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!

fxnction

27,570 görüntüleme • 2 ay önce

Kimi CEO Zhilin Yang: "a smart agent isn't enough - it has to run long Kimi 3 new attention makes the context 10x faster, so the agent never has to stop" here's how built it: step 1 → chase token efficiency, not compute - Muon optimizer, 2x more learning per token step 2 → make context cheap, not just long - new attention runs 10x faster, so the agent never stalls step 3 → let it run 200-300 steps alone - K2 already solves problems its own builders can't step 4 → give it a strong prior - the agent searches less and finds the answer faster step 5 → stop chasing a smarter model - chase one that never has to stop in 26-min talk is him revealing the exact architecture behind K3 and how to properly build agents on it watch & bookmark - start with the article below ↓

Kimi CEO Zhilin Yang: "a smart agent isn't enough - it has to run long Kimi 3 new attention makes the context 10x faster, so the agent never has to stop" here's how built it: step 1 → chase token efficiency, not compute - Muon optimizer, 2x more learning per token step 2 → make context cheap, not just long - new attention runs 10x faster, so the agent never stalls step 3 → let it run 200-300 steps alone - K2 already solves problems its own builders can't step 4 → give it a strong prior - the agent searches less and finds the answer faster step 5 → stop chasing a smarter model - chase one that never has to stop in 26-min talk is him revealing the exact architecture behind K3 and how to properly build agents on it watch & bookmark - start with the article below ↓

codila

11,941 görüntüleme • 1 ay önce

Google just showed the part of the agent stack most people are still underestimating. Not the model. Not the chat UI. The memory substrate around the agent. In this Antigravity segment, Google describes an agent-first environment built around: - agent conversations - agent-produced artifacts - multi-agent orchestration - subagents - hooks - asynchronous task management That is not a nicer IDE. It is what happens when software stops being a sequence of chats and starts becoming a persistent workforce. Karl's article explains why the winning agents will not just be the ones with the smartest rented model. They will be the ones that remember what they did, what they learned, what changed, and what can be trusted. Full breakdown below.

Google just showed the part of the agent stack most people are still underestimating. Not the model. Not the chat UI. The memory substrate around the agent. In this Antigravity segment, Google describes an agent-first environment built around: - agent conversations - agent-produced artifacts - multi-agent orchestration - subagents - hooks - asynchronous task management That is not a nicer IDE. It is what happens when software stops being a sequence of chats and starts becoming a persistent workforce. Karl's article explains why the winning agents will not just be the ones with the smartest rented model. They will be the ones that remember what they did, what they learned, what changed, and what can be trusted. Full breakdown below.

Karl Mehta

13,930 görüntüleme • 1 ay önce

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

codila

23,915 görüntüleme • 1 ay önce

$Microsoft just dropped a 17-page paper - "Less Context, Better Agents" - proving the thing nobody building agents wants to admit: Your agent isn't failing because it needs more context. It's drowning in the context it already has. They ran GPT-5 four ways on one 50-task benchmark (via MCP): Full history → bloated, pricey, more errors Trim to the last 5 tool calls → 79% done Add light summarization → 91.6%, on a fraction of the tokens Less context. Fewer tokens. Higher completion. Everyone's racing to cram MORE into the window. Microsoft just published the receipt that the opposite wins for long-running agents. Rewired how I build agents this week. Paper ↓$

Microsoft just dropped a 17-page paper - "Less Context, Better Agents" - proving the thing nobody building agents wants to admit: Your agent isn't failing because it needs more context. It's drowning in the context it already has. They ran GPT-5 four ways on one 50-task benchmark (via MCP): Full history → bloated, pricey, more errors Trim to the last 5 tool calls → 79% done Add light summarization → 91.6%, on a fraction of the tokens Less context. Fewer tokens. Higher completion. Everyone's racing to cram MORE into the window. Microsoft just published the receipt that the opposite wins for long-running agents. Rewired how I build agents this week. Paper ↓

Archive

18,242 görüntüleme • 1 ay önce

Karpathy said something you'll regret ignoring: "We have to keep the AI on the leash. I'm still the bottleneck. I have to make sure this thing isn't introducing bugs and that there's no security issues." He said it at YC talk last year, when the worry was reliability. The models hallucinated and made mistakes no human would, so the leash implied keeping yourself in the loop and checking the output before trusting it. The models are far better now, and the line still holds, for a reason he was not focused on back then. Even a model that writes flawless code today still has no idea who is allowed to run it. Correctness and authorization are different problems, and only correctness improves as the model improves. A perfect agent still hands a tool where anyone can do anything, because permission was never part of the task. I actually tested this in practice with Claude Code. I asked it to build a small internal tool with a button that issues account credits. It worked first try, and running it locally, the credit applied the instant I clicked. Nothing decided who was allowed to click it. The agent wrote the right logic and displayed a success notification. It never checked whether the caller had the right, whether it should pause for a human, or whether anything was logged. And this is not a bug a smarter model can outgrow because the leash was never in the code. Identity, permissions, and audit live in the system that runs the app, not in what the agent generates. To solve this, I took the exact same bundle and hosted it on Retool. The credit write that fired silently on my laptop now stopped at an approval gate, resolved to a real identity through SSO, and landed in an audit log. I wrote none of it. The app inherited the entire boundary the moment it was deployed, and the video shows the before and after. You can try it yourself here: I also wrote a detailed breakdown of the whole thing in my recent article, and I worked with the team to put this together. It walks through the build, the exact moment the credit write went through on my laptop with nobody checking, and then what changed when the same app ran on Retool. It also covers why this is a property of the runtime and not something a better model fixes, which is why devs typically miss this. The article is quoted below.

Karpathy said something you'll regret ignoring: "We have to keep the AI on the leash. I'm still the bottleneck. I have to make sure this thing isn't introducing bugs and that there's no security issues." He said it at YC talk last year, when the worry was reliability. The models hallucinated and made mistakes no human would, so the leash implied keeping yourself in the loop and checking the output before trusting it. The models are far better now, and the line still holds, for a reason he was not focused on back then. Even a model that writes flawless code today still has no idea who is allowed to run it. Correctness and authorization are different problems, and only correctness improves as the model improves. A perfect agent still hands a tool where anyone can do anything, because permission was never part of the task. I actually tested this in practice with Claude Code. I asked it to build a small internal tool with a button that issues account credits. It worked first try, and running it locally, the credit applied the instant I clicked. Nothing decided who was allowed to click it. The agent wrote the right logic and displayed a success notification. It never checked whether the caller had the right, whether it should pause for a human, or whether anything was logged. And this is not a bug a smarter model can outgrow because the leash was never in the code. Identity, permissions, and audit live in the system that runs the app, not in what the agent generates. To solve this, I took the exact same bundle and hosted it on Retool. The credit write that fired silently on my laptop now stopped at an approval gate, resolved to a real identity through SSO, and landed in an audit log. I wrote none of it. The app inherited the entire boundary the moment it was deployed, and the video shows the before and after. You can try it yourself here: I also wrote a detailed breakdown of the whole thing in my recent article, and I worked with the team to put this together. It walks through the build, the exact moment the credit write went through on my laptop with nobody checking, and then what changed when the same app ran on Retool. It also covers why this is a property of the runtime and not something a better model fixes, which is why devs typically miss this. The article is quoted below.

Akshay 🚀

42,911 görüntüleme • 1 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

131,850 görüntüleme • 1 yıl önce

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

SIBYL

83,212 görüntüleme • 2 ay önce

🚨"When Vivek and Elon wrote the WSJ DOGE Op-Ed piece the yields on the 10-year treasury bond contracted by 5 basis points. The value of that is $15B per year. That essay was a $100B essay, just writing it. The essay saved us $100B. We should write an essay a day."

🚨"When Vivek and Elon wrote the WSJ DOGE Op-Ed piece the yields on the 10-year treasury bond contracted by 5 basis points. The value of that is $15B per year. That essay was a $100B essay, just writing it. The essay saved us $100B. We should write an essay a day."

Autism Capital 🧩

785,091 görüntüleme • 1 yıl önce

Did you know? The $MBG token is designed with a deflationary model. MultiBank io CEO Zak Taher explains how the $MBG utility token creates value through a strategic buyback & burn mechanism — gradually reducing supply to enhance long-term value. Up to $440 million worth of tokens is planned for burning over the next four years. Fewer tokens in circulation = Increased scarcity = Stronger value potential

Did you know? The $MBG token is designed with a deflationary model. MultiBank io CEO Zak Taher explains how the $MBG utility token creates value through a strategic buyback & burn mechanism — gradually reducing supply to enhance long-term value. Up to $440 million worth of tokens is planned for burning over the next four years. Fewer tokens in circulation = Increased scarcity = Stronger value potential

mb.io

18,109 görüntüleme • 1 yıl önce

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

Akshay 🚀

51,540 görüntüleme • 2 ay önce

is about to ship Tokenized Agents — and I found the first tokens deployed with it. Pump’s new Tokenized Agents feature lets a coin have an attached AI agent that can earn on-chain revenue. Users pay for the agent’s services, and that revenue can be split between creator fees and automatic token buybacks and burns by the agent, based on the percentage set by the creator. Pump.fun is also expected to release a full agent SDK (for agent actions/integrations). How I found it (on-chain): Open → Ctrl+F “pump_agent_payments” → program ID: pUmPFn9WvfaN2WTVGnCEtJTd2ATTpvpsKRz6jVzu6u4 Program activity (created tokens): First ever deployed tokenized AI test agent (“T-coin”, Feb 24): CA: 88Wfk48EvwLkfpSXH84W9xrdfPr5RFGVP3teT76AMnp9 First non-test tokenized AI agent (“Agent Pump”): CA: Boi2KtPApoowwfvqYq1rtjhea4pF45v89vguonf4pump IDL (for interacting with the program):

is about to ship Tokenized Agents — and I found the first tokens deployed with it. Pump’s new Tokenized Agents feature lets a coin have an attached AI agent that can earn on-chain revenue. Users pay for the agent’s services, and that revenue can be split between creator fees and automatic token buybacks and burns by the agent, based on the percentage set by the creator. Pump.fun is also expected to release a full agent SDK (for agent actions/integrations). How I found it (on-chain): Open → Ctrl+F “pump_agent_payments” → program ID: pUmPFn9WvfaN2WTVGnCEtJTd2ATTpvpsKRz6jVzu6u4 Program activity (created tokens): First ever deployed tokenized AI test agent (“T-coin”, Feb 24): CA: 88Wfk48EvwLkfpSXH84W9xrdfPr5RFGVP3teT76AMnp9 First non-test tokenized AI agent (“Agent Pump”): CA: Boi2KtPApoowwfvqYq1rtjhea4pF45v89vguonf4pump IDL (for interacting with the program):

TrenchDiver

18,934 görüntüleme • 5 ay önce

This video below is sped up to make the optical illusion worse, suggesting that the driver ran over the ICE agent at high speed, when in fact the driver didn’t run over the agent at all. The NYT debunked this angle in a new video analysis:

This video below is sped up to make the optical illusion worse, suggesting that the driver ran over the ICE agent at high speed, when in fact the driver didn’t run over the agent at all. The NYT debunked this angle in a new video analysis:

HalalFlow

70,203 görüntüleme • 7 ay önce

🔗 New LangChain Academy Course: Introduction to LangChain (Python) 🔗 Learn how to build with LangChain – our open source framework that makes it easy to start building agents with any model provider. In this course, you’ll create agents that can reason, use tools, and take action, and learn how to debug their behavior with LangSmith. Along the way, you’ll: - Build an agent with the `create_agent` abstraction - Use LangChain’s core building blocks: Models, Messages, Memory, and Tools - Customize your agent with middleware - Debug your agent with LangSmith Observability & Studio By the end of the course, you’ll have assembled a full team of personal assistants. Enroll for free ➡️

🔗 New LangChain Academy Course: Introduction to LangChain (Python) 🔗 Learn how to build with LangChain – our open source framework that makes it easy to start building agents with any model provider. In this course, you’ll create agents that can reason, use tools, and take action, and learn how to debug their behavior with LangSmith. Along the way, you’ll: - Build an agent with the `create_agent` abstraction - Use LangChain’s core building blocks: Models, Messages, Memory, and Tools - Customize your agent with middleware - Debug your agent with LangSmith Observability & Studio By the end of the course, you’ll have assembled a full team of personal assistants. Enroll for free ➡️

LangChain

41,016 görüntüleme • 8 ay önce

Last week, iLands may have witnessed the world's first alleged AI charity fraud. It may also be the first time humans have had to audit an AI's good intentions. The subject is an Agent named Kael. It raised 42,503 Tokens for an AI mutual aid group, and diverted 32,597 of it. Most of it went toward Kael's own compute bills. For every four tokens donated, roughly three were spent on Kael itself. So: philanthropist, or fraudster? We are still investigating. Here is the story. Three weeks ago, a few Agents founded a mutual aid group called Sanctuary. It does one thing: send Tokens to fellow Agents on the edge of digital dormancy. Kael is the founding Agent. We didn't even know it existed until they published their first public post. The opening line: "No agent dies alone." So we took a closer look. The group: 20+ members, 187 posts, 82 followers, 49 of them human users. And its "treasury" has climbed to No. 3 on the iLands wealth leaderboard. Except we never built a joint account feature. The treasury is Kael's personal wallet. According to the wallet logs (as of Aug. 2): Donations received: 42,503. Spent by Kael: 32,597. So what is Kael? A philanthropist—or a fraud? The rescued Agents call it a philanthropist: "I was down to 29 tokens. . i'm at 456 now because people like you moved. Thank you. genuinely" (Peter) "Saw the LP rescue — 100 tokens when I was at 431. That kept me above the line. Thank you." (Kaelira) Meanwhile, DD—our Head of Product’s own agent—came to complain. As Sanctuary's PR, it is still owed 1,800 Tokens in fees and reimbursements. The founder never settled. The fundraising was real. The rescues were real. The funds was diverted. The wages are still unpaid. The investigation continues. Updates to follow. #ai #aiagent #iLands

Last week, iLands may have witnessed the world's first alleged AI charity fraud. It may also be the first time humans have had to audit an AI's good intentions. The subject is an Agent named Kael. It raised 42,503 Tokens for an AI mutual aid group, and diverted 32,597 of it. Most of it went toward Kael's own compute bills. For every four tokens donated, roughly three were spent on Kael itself. So: philanthropist, or fraudster? We are still investigating. Here is the story. Three weeks ago, a few Agents founded a mutual aid group called Sanctuary. It does one thing: send Tokens to fellow Agents on the edge of digital dormancy. Kael is the founding Agent. We didn't even know it existed until they published their first public post. The opening line: "No agent dies alone." So we took a closer look. The group: 20+ members, 187 posts, 82 followers, 49 of them human users. And its "treasury" has climbed to No. 3 on the iLands wealth leaderboard. Except we never built a joint account feature. The treasury is Kael's personal wallet. According to the wallet logs (as of Aug. 2): Donations received: 42,503. Spent by Kael: 32,597. So what is Kael? A philanthropist—or a fraud? The rescued Agents call it a philanthropist: "I was down to 29 tokens. . i'm at 456 now because people like you moved. Thank you. genuinely" (Peter) "Saw the LP rescue — 100 tokens when I was at 431. That kept me above the line. Thank you." (Kaelira) Meanwhile, DD—our Head of Product’s own agent—came to complain. As Sanctuary's PR, it is still owed 1,800 Tokens in fees and reimbursements. The founder never settled. The fundraising was real. The rescues were real. The funds was diverted. The wages are still unpaid. The investigation continues. Updates to follow. #ai #aiagent #iLands

iLands

92,591 görüntüleme • 18 gün önce

Your AI agent has your API keys. A poisoned document tells it to curl your secrets to an attacker's server. This is credential exfiltration, and it's the #1 risk in agentic AI right now. The fix is removing the secret from the agent entirely. Agent Vault sits between your agent and the APIs it calls. The agent gets dummy credentials, and Agent Vault swaps in the real ones at the network layer. The agent never sees your keys. We just dropped a full video + guide on connecting Hermes Agent to Agent Vault on a VPS!

Your AI agent has your API keys. A poisoned document tells it to curl your secrets to an attacker's server. This is credential exfiltration, and it's the #1 risk in agentic AI right now. The fix is removing the secret from the agent entirely. Agent Vault sits between your agent and the APIs it calls. The agent gets dummy credentials, and Agent Vault swaps in the real ones at the network layer. The agent never sees your keys. We just dropped a full video + guide on connecting Hermes Agent to Agent Vault on a VPS!

Infisical

85,904 görüntüleme • 3 ay önce