Загрузка видео...

Не удалось загрузить видео

На главную

An agent is three things: a harness, a model, and context. If you're serious about owning your intelligence, you probably want to own all three. LangChain founder Harrison Chase joined us at our Sequoia Capital Own Your Intelligence to talk about the piece that often gets the least attention:...

sonyatweetybird's profile picture

Sonya Huang 🐥

28,118 subscribers

74,288 просмотров • 3 дней назад •via X (Twitter)

Наука и технологииОбразованиеНовости и политика
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

When should you start post-training your own models? Fireworks CEO Lin Qiao’s answer: after product-market fit. Not because it's hard... but because only after PMF is the data coming off your product surface worth training on. Lin joined us for our Sequoia Capital "Own Your Intelligence" event to host a workshop on all things post-training; what works, what breaks, and how not to let the model outsmart you. Must listen!! 00:00 Introduction 00:37 What Fireworks sees across thousands of AI applications 02:47 Off-the-shelf APIs and the problem of keeping your taste 03:58 What "owning your intelligence" actually means 05:43 The progression: prompting → RAG → SFT → preferences → RL 07:20 Why this mirrors how humans learn 09:03 Matching the technique to the problem you actually have 10:46 Where teams get stuck: data quality and vibe evals 12:28 Reward hacking: the model that wrote zero lines of code 13:59 Training-to-serving alignment (and why quality drops) 15:55 Post-training in healthcare and security 17:31 From coding to every co-work domain 19:35 Incumbents, cost burden, and not scaling into bankruptcy 21:26 How much control do you want? 23:24 Q&A: What makes a good reward signal 25:00 Q&A: When to start thinking about post-training
28:28

When should you start post-training your own models? Fireworks CEO Lin Qiao’s answer: after product-market fit. Not because it's hard... but because only after PMF is the data coming off your product surface worth training on. Lin joined us for our Sequoia Capital "Own Your Intelligence" event to host a workshop on all things post-training; what works, what breaks, and how not to let the model outsmart you. Must listen!! 00:00 Introduction 00:37 What Fireworks sees across thousands of AI applications 02:47 Off-the-shelf APIs and the problem of keeping your taste 03:58 What "owning your intelligence" actually means 05:43 The progression: prompting → RAG → SFT → preferences → RL 07:20 Why this mirrors how humans learn 09:03 Matching the technique to the problem you actually have 10:46 Where teams get stuck: data quality and vibe evals 12:28 Reward hacking: the model that wrote zero lines of code 13:59 Training-to-serving alignment (and why quality drops) 15:55 Post-training in healthcare and security 17:31 From coding to every co-work domain 19:35 Incumbents, cost burden, and not scaling into bankruptcy 21:26 How much control do you want? 23:24 Q&A: What makes a good reward signal 25:00 Q&A: When to start thinking about post-training

Sonya Huang 🐥

23,604 просмотров • 4 дней назад

Everything Gets Rebuilt: my conversation with Harrison Chase, CEO of LangChain about agent harnesses, evals, runtimes, sandboxes, MCP and the future of the agent stack 00:00 Intro - meet Harrison Chase - at the Chase Center for the Daytona Compute conference 01:32 What changed in agents over the last year 03:57 Why coding agents are ahead 06:26 Do models commoditize the framework layer? 08:27 Harnesses, in plain English 10:11 Why system prompts matter so much 13:11 The upside — and downside — of subagents 15:31 Why a useful agent needs a filesystem 18:13 Additional core primitives of modern agents 19:12 Skills: the new primitive 20:19 What context compaction actually means 23:02 How memory works in agents 25:16 One mega-agent or many specialized agents? 27:46 The future of MCP 29:38 Why agents need sandboxes 32:35 How sandboxes help with security 33:32 How Harrison Chase started LangChain 37:24 LangChain vs LangGraph vs Deep Agents 40:17 Why observability matters more for agents 41:48 Evals, no-code, and continuous improvement 44:41 What LangChain is building next 45:29 Where the real moat in AI lives
46:57

Everything Gets Rebuilt: my conversation with Harrison Chase, CEO of LangChain about agent harnesses, evals, runtimes, sandboxes, MCP and the future of the agent stack 00:00 Intro - meet Harrison Chase - at the Chase Center for the Daytona Compute conference 01:32 What changed in agents over the last year 03:57 Why coding agents are ahead 06:26 Do models commoditize the framework layer? 08:27 Harnesses, in plain English 10:11 Why system prompts matter so much 13:11 The upside — and downside — of subagents 15:31 Why a useful agent needs a filesystem 18:13 Additional core primitives of modern agents 19:12 Skills: the new primitive 20:19 What context compaction actually means 23:02 How memory works in agents 25:16 One mega-agent or many specialized agents? 27:46 The future of MCP 29:38 Why agents need sandboxes 32:35 How sandboxes help with security 33:32 How Harrison Chase started LangChain 37:24 LangChain vs LangGraph vs Deep Agents 40:17 Why observability matters more for agents 41:48 Evals, no-code, and continuous improvement 44:41 What LangChain is building next 45:29 Where the real moat in AI lives

Matt Turck

35,253 просмотров • 5 месяцев назад

A model is only as good as its data, and we’ve long since exhausted the internet. From here on out, model progress is gated by data production. ’s Brendan (can/do) joined us at our Sovereign AI event to talk about how RL environments get built, and why your data might be your real moat: 00:00 Introduction 00:47 A short history of the data market: crowdsourcing to agentic data 02:29 What an RL environment is: worlds, apps, tasks 03:57 Why only humans can measure the frontier 05:35 Building verifiers is the hard part 06:44 Walkthrough: a real legal RL environment 08:18 Leaderboards — and what open weights change 09:45 Post-training results on Apex Agents 11:17 Three ways companies buy data 12:49 Q&A: How do you price data? 14:17 Q&A: What "data quality" actually means 16:42 Q&A: The misunderstanding about synthetic data 18:17 Q&A: Why RL environments now — and what comes after 21:20 Q&A: Can you scale rubric generation with models? 23:00 Q&A: RL environments for cyber defense 25:33 Q&A: Build data in-house or partner?
26:21

A model is only as good as its data, and we’ve long since exhausted the internet. From here on out, model progress is gated by data production. ’s Brendan (can/do) joined us at our Sovereign AI event to talk about how RL environments get built, and why your data might be your real moat: 00:00 Introduction 00:47 A short history of the data market: crowdsourcing to agentic data 02:29 What an RL environment is: worlds, apps, tasks 03:57 Why only humans can measure the frontier 05:35 Building verifiers is the hard part 06:44 Walkthrough: a real legal RL environment 08:18 Leaderboards — and what open weights change 09:45 Post-training results on Apex Agents 11:17 Three ways companies buy data 12:49 Q&A: How do you price data? 14:17 Q&A: What "data quality" actually means 16:42 Q&A: The misunderstanding about synthetic data 18:17 Q&A: Why RL environments now — and what comes after 21:20 Q&A: Can you scale rubric generation with models? 23:00 Q&A: RL environments for cyber defense 25:33 Q&A: Build data in-house or partner?

Pat Grady

63,548 просмотров • 4 дней назад

Intelligence and Experience are orthogonal vectors Terence Tao is perhaps the world’s smartest person, but drop him into an accounting firm or onto a construction site and on day one he’s not going to be very productive Trajectory calls this The Experience Gap, and they have a way to close it Arjun Karanam explained how at our Sovereign AI event: 00:00 Introduction 00:12 Building the platform for continual learning 01:33 The experience gap: models have IQ but no tenure 02:52 Traceability → model spec → better models and harnesses 05:27 Four wishes for the agent ecosystem 06:34 Wish 1: Trace the whole tree — and capture the corrections 08:03 Wish 2: Evals from real traffic, graded in the real harness 09:26 Wish 3: Let the agents cook, and make tool responses informative 10:34 Wish 4: Get comfortable on open weights, experiment with routers 11:51 Why owning your intelligence shouldn't be consulted away 13:15 Demo: import a benchmark, train a model, deploy it 14:28 Q&A: What's the trainable object — weights, harness, or context? 16:08 Q&A: Continual learning without training on customer data 17:13 Q&A: Episodic memory and the hierarchy of feedback 19:37 Q&A: Where continual learning matters most
21:55

Intelligence and Experience are orthogonal vectors Terence Tao is perhaps the world’s smartest person, but drop him into an accounting firm or onto a construction site and on day one he’s not going to be very productive Trajectory calls this The Experience Gap, and they have a way to close it Arjun Karanam explained how at our Sovereign AI event: 00:00 Introduction 00:12 Building the platform for continual learning 01:33 The experience gap: models have IQ but no tenure 02:52 Traceability → model spec → better models and harnesses 05:27 Four wishes for the agent ecosystem 06:34 Wish 1: Trace the whole tree — and capture the corrections 08:03 Wish 2: Evals from real traffic, graded in the real harness 09:26 Wish 3: Let the agents cook, and make tool responses informative 10:34 Wish 4: Get comfortable on open weights, experiment with routers 11:51 Why owning your intelligence shouldn't be consulted away 13:15 Demo: import a benchmark, train a model, deploy it 14:28 Q&A: What's the trainable object — weights, harness, or context? 16:08 Q&A: Continual learning without training on customer data 17:13 Q&A: Episodic memory and the hierarchy of feedback 19:37 Q&A: Where continual learning matters most

Pat Grady

72,044 просмотров • 4 дней назад

The founder of LangChain says both models and harnesses have gotten really good between December and now. According to Harrison Chase, the core idea of an agent before Christmas was a model running in a loop and calling tools. This had been the north star for 3 years. - langchain had this when it launched - autogpt was the same idea - openclaw is kind of a future version of it Then about a year ago, they started getting really good. Claude Code, Manus, and Deep Research were all launched around the same time. All of them use the same pattern: running in a loop with harnesses (planning tools, file systems, code execution, etc) Harness engineering became a thing. Then Opus came out in November and really unlocked it. - the harness let the model do more and more - less hardcoded logic - way more control Then everyone went on vacation, played around, and realized that the model and the harness finally worked reliably.
2:10

The founder of LangChain says both models and harnesses have gotten really good between December and now. According to Harrison Chase, the core idea of an agent before Christmas was a model running in a loop and calling tools. This had been the north star for 3 years. - langchain had this when it launched - autogpt was the same idea - openclaw is kind of a future version of it Then about a year ago, they started getting really good. Claude Code, Manus, and Deep Research were all launched around the same time. All of them use the same pattern: running in a loop with harnesses (planning tools, file systems, code execution, etc) Harness engineering became a thing. Then Opus came out in November and really unlocked it. - the harness let the model do more and more - less hardcoded logic - way more control Then everyone went on vacation, played around, and realized that the model and the harness finally worked reliably.

Ivan Burazin

33,948 просмотров • 4 месяцев назад

OWN YOUR INTELLIGENCE Last year, building on open-weight models was primarily a cost rationalization exercise. Slightly worse performance for a much cheaper price. Now, it is increasingly an existential and strategic topic for our portfolio. Intelligence is the product. Companies want to shape it and own it and let it compound within their own walls. Not your weights, not your product. Now, with frontier open-weight models and fantastic tooling/infrastructure, owning your intelligence at the frontier is finally becoming possible. The result: every application company we work with is embarking on the journey of doing their own research on post-training, evals, harnesses, etc. The hottest neolabs may just be Harvey, Factory, RamPrasad "RamP!" Moudgalya, etc. The list goes on. We held a summit Sequoia Capital to convene our portfolio on this topic, together with Gabe Pereyra (Harvey) on building Harvey Labs, Lin Qiao (Fireworks) on post-training, Harrison Chase (LangChain) on harnesses + evals, Brendan (can/do) () on RL environments and synthetic data, Arjun Karanam (Trajectory) on online continual learning. Opening talk below; rest to come this week! 00:00 What is sovereign AI (and what it isn't) 01:24 Centralized vs. decentralized intelligence 02:54 Four reasons companies own their models: cost, speed, performance, destiny 04:22 "Not your weights, not your product" 05:32 The application companies are the newest neo labs 07:05 Step 1: Deciding what to own vs. rent 09:51 Step 2: Build the team (and don't shoehorn your platform team) 11:17 Step 3: Legibility – why your research has to be visible 12:33 Step 4: The technical roadmap 13:56 The stack: production vs. development 15:16 Opening Pandora's box – base models, harnesses, context
17:28

OWN YOUR INTELLIGENCE Last year, building on open-weight models was primarily a cost rationalization exercise. Slightly worse performance for a much cheaper price. Now, it is increasingly an existential and strategic topic for our portfolio. Intelligence is the product. Companies want to shape it and own it and let it compound within their own walls. Not your weights, not your product. Now, with frontier open-weight models and fantastic tooling/infrastructure, owning your intelligence at the frontier is finally becoming possible. The result: every application company we work with is embarking on the journey of doing their own research on post-training, evals, harnesses, etc. The hottest neolabs may just be Harvey, Factory, RamPrasad "RamP!" Moudgalya, etc. The list goes on. We held a summit Sequoia Capital to convene our portfolio on this topic, together with Gabe Pereyra (Harvey) on building Harvey Labs, Lin Qiao (Fireworks) on post-training, Harrison Chase (LangChain) on harnesses + evals, Brendan (can/do) () on RL environments and synthetic data, Arjun Karanam (Trajectory) on online continual learning. Opening talk below; rest to come this week! 00:00 What is sovereign AI (and what it isn't) 01:24 Centralized vs. decentralized intelligence 02:54 Four reasons companies own their models: cost, speed, performance, destiny 04:22 "Not your weights, not your product" 05:32 The application companies are the newest neo labs 07:05 Step 1: Deciding what to own vs. rent 09:51 Step 2: Build the team (and don't shoehorn your platform team) 11:17 Step 3: Legibility – why your research has to be visible 12:33 Step 4: The technical roadmap 13:56 The stack: production vs. development 15:16 Opening Pandora's box – base models, harnesses, context

Sonya Huang 🐥

123,318 просмотров • 5 дней назад

Every agent needs its own computer: my conversation with Ivan Burazin, CEO of Daytona, about sandboxes and the emerging agent stack. 00:00 Intro 02:13 What is an AI agent sandbox? 03:17 Security risks of running agents locally 05:17 Stateful vs. stateless hyperscalers 07:04 The history of cloud IDEs and the end of localhost 09:45 Do all AI agents need a sandbox? 12:26 Sandbox use cases: RL evals & background agents 14:10 Unpacking the emerging AI Agent Stack 16:20 The unsolved problem of agent memory and learning 19:37 Where sandboxes fit in the agent harness 21:35 OpenAI, Anthropic, and agent SDKs 23:06 Ivan's founder journey: From CodeAnywhere to Daytona 26:59 GTM strategies and building developer communities 33:48 Why customer support is your best GTM strategy 35:34 Leveraging Twitter during the AI super cycle 40:50 The technical anatomy of a sandbox 41:53 Why fast spin-up speeds maximize GPU efficiency 46:09 Firecracker, QEMU, and isolation primitives 49:58 Why sandbox snapshots and state forking matter 51:40 Why Daytona built a custom scheduler from scratch 55:24 The challenge of long-running stateful sandboxes 58:10 The build your own sandbox trap 1:01:03 Why AI agents might trigger a global CPU shortage 1:02:46 The future of the AI Agent Stack
1:05:15

Every agent needs its own computer: my conversation with Ivan Burazin, CEO of Daytona, about sandboxes and the emerging agent stack. 00:00 Intro 02:13 What is an AI agent sandbox? 03:17 Security risks of running agents locally 05:17 Stateful vs. stateless hyperscalers 07:04 The history of cloud IDEs and the end of localhost 09:45 Do all AI agents need a sandbox? 12:26 Sandbox use cases: RL evals & background agents 14:10 Unpacking the emerging AI Agent Stack 16:20 The unsolved problem of agent memory and learning 19:37 Where sandboxes fit in the agent harness 21:35 OpenAI, Anthropic, and agent SDKs 23:06 Ivan's founder journey: From CodeAnywhere to Daytona 26:59 GTM strategies and building developer communities 33:48 Why customer support is your best GTM strategy 35:34 Leveraging Twitter during the AI super cycle 40:50 The technical anatomy of a sandbox 41:53 Why fast spin-up speeds maximize GPU efficiency 46:09 Firecracker, QEMU, and isolation primitives 49:58 Why sandbox snapshots and state forking matter 51:40 Why Daytona built a custom scheduler from scratch 55:24 The challenge of long-running stateful sandboxes 58:10 The build your own sandbox trap 1:01:03 Why AI agents might trigger a global CPU shortage 1:02:46 The future of the AI Agent Stack

Matt Turck

11,908 просмотров • 3 месяцев назад

New session with Shreya Shankar on How to Automate Evals with AI (correctly) The most important part of the eval workflow is finding issues. Shreya does a live demo of how to steer the AI iteratively to find unknown unknowns Chapter summaries: 00:00:00 Introduction 00:00:55 Why vendors want to automate evals for you 00:01:45 Why no tool can fully automate evals 00:06:00 Mistake #1: Asking AI to just "find the issues" in your data 00:08:11 What good AI-assisted error analysis actually looks like 00:11:12 Live demo: building a review interface from scratch 00:15:10 Annotating traces and building a failure mode taxonomy 00:19:31 Mistake #2: Only reviewing your data once 00:22:53 Mistake #3: Treating all apps with the same accuracy bar 00:25:10 General-purpose agents vs. dedicated eval tools 00:25:48 Summary: three rules for automating evals correctly YT links and more in reply
27:18

New session with Shreya Shankar on How to Automate Evals with AI (correctly) The most important part of the eval workflow is finding issues. Shreya does a live demo of how to steer the AI iteratively to find unknown unknowns Chapter summaries: 00:00:00 Introduction 00:00:55 Why vendors want to automate evals for you 00:01:45 Why no tool can fully automate evals 00:06:00 Mistake #1: Asking AI to just "find the issues" in your data 00:08:11 What good AI-assisted error analysis actually looks like 00:11:12 Live demo: building a review interface from scratch 00:15:10 Annotating traces and building a failure mode taxonomy 00:19:31 Mistake #2: Only reviewing your data once 00:22:53 Mistake #3: Treating all apps with the same accuracy bar 00:25:10 General-purpose agents vs. dedicated eval tools 00:25:48 Summary: three rules for automating evals correctly YT links and more in reply

Hamel Husain

34,196 просмотров • 1 месяц назад

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11
43:20

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

Dan Shipper 📧

66,339 просмотров • 3 месяцев назад

You Can Learn AI Agent Harness & Loop Engineering In 19 Min, with LLM Ops, Eval, Tracing and RAG. They went viral not because they're complicated but because they're simple building blocks, and once you see them you can prompt your way to building real systems. 🎬YouTube: Here's the whole thing in one picture. An LLM is a powerful brain that knows everything about humanity and nothing about you or the software you're running. The harness is the set of tools you put on that horse so it runs where you want. Memory gives it context: who you are, what happened before, how to act. The loop lets it call tools again and again, with guardrails so it knows when to stop. Eval and LLM Ops trace every run, score it, and feed the fixes back in so the system keeps improving itself. Master these four and you can read almost any AI agent repo or paper and actually know what's going on. You Can Build Anything. You Can Learn Anything. 💪 Chapters: Intro: the 4 AI agent buzzwords What an AI agent run actually is The memory system: procedural, semantic, episodic What "harness" really means (the horse) Storing and updating memory (databases, skills, summarizer agent) Retrieval: RAG, SQL vs semantic search Tool calling and why agents loop Loop engineering and end-loop guardrails A Claude Code hooks example Eval and LLM Ops: why you need them Tracing every run (Langfuse, LangSmith) Evaluation: LLM as a judge Diagnosing what broke The gate: ship the fix or fix the bug Zoom out: the full system
19:59

You Can Learn AI Agent Harness & Loop Engineering In 19 Min, with LLM Ops, Eval, Tracing and RAG. They went viral not because they're complicated but because they're simple building blocks, and once you see them you can prompt your way to building real systems. 🎬YouTube: Here's the whole thing in one picture. An LLM is a powerful brain that knows everything about humanity and nothing about you or the software you're running. The harness is the set of tools you put on that horse so it runs where you want. Memory gives it context: who you are, what happened before, how to act. The loop lets it call tools again and again, with guardrails so it knows when to stop. Eval and LLM Ops trace every run, score it, and feed the fixes back in so the system keeps improving itself. Master these four and you can read almost any AI agent repo or paper and actually know what's going on. You Can Build Anything. You Can Learn Anything. 💪 Chapters: Intro: the 4 AI agent buzzwords What an AI agent run actually is The memory system: procedural, semantic, episodic What "harness" really means (the horse) Storing and updating memory (databases, skills, summarizer agent) Retrieval: RAG, SQL vs semantic search Tool calling and why agents loop Loop engineering and end-loop guardrails A Claude Code hooks example Eval and LLM Ops: why you need them Tracing every run (Langfuse, LangSmith) Evaluation: LLM as a judge Diagnosing what broke The gate: ship the fix or fix the bug Zoom out: the full system

Shen Sean Chen

15,952 просмотров • 1 месяц назад

A lot of people are calling Hermes Agent the end of OpenClaw. BRUH! It's not... Nous Research trains actual models and they built an agent around that expertise. The local model routing is solid, but the part that matters for your business is that your conversations become fine-tuning data. You can train a model on how you actually work. 00:00 The Problem with Local AI Models 00:25 Introduction to Nous Research 01:04 Cross-Platform Agent Capabilities 01:44 Deep Local Model Integration 02:30 Routing Tasks to Different Models 03:06 Conversations as Training Data 03:50 Hermes Agent vs. OpenClaw 04:15 Future Plans and Series Overview
4:45

A lot of people are calling Hermes Agent the end of OpenClaw. BRUH! It's not... Nous Research trains actual models and they built an agent around that expertise. The local model routing is solid, but the part that matters for your business is that your conversations become fine-tuning data. You can train a model on how you actually work. 00:00 The Problem with Local AI Models 00:25 Introduction to Nous Research 01:04 Cross-Platform Agent Capabilities 01:44 Deep Local Model Integration 02:30 Routing Tasks to Different Models 03:06 Conversations as Training Data 03:50 Hermes Agent vs. OpenClaw 04:15 Future Plans and Series Overview

Ray Fernando

42,398 просмотров • 4 месяцев назад

Watch what Nadella did on the Microsoft earnings call tonight. An analyst asked how Microsoft benefits from enterprises adopting open models when it carries all that frontier lab exposure. Instead of defending the lab relationship, Nadella laid out an architecture: "You've got to keep your harness separate from the model. The harness will ensure that your memory, your context, all of that is external. That means any given model at any given time is swappable." And then the part that should worry anyone underwriting model moats: use frontier models where they earn it, low-cost models where they don't, "and in fact, train your own model when you don't want to use any external model itself because after all, you have all the outputs, you have all the traces, you have all the context." The firm keeps the harness. The models compete for slots inside it. Jensen Huang said most companies will be built on harnesses at the LangChain fireside on July 8. I published the full framework on July 12, five launches in three days, all converging on the same architecture. Tonight the largest enterprise software company on earth made it the official pitch on an earnings call. The moat question in enterprise AI just moved from who has the best weights to who owns the loop around them. And if the completed task is the unit everyone now competes on, someone has to price it for the buyer. That is the next thing we are building at BEP Research: a cost per task tool for enterprises. More on that soon. I also took the paywall off the full framework piece tonight, so the whole thing is free to read:
1:15

Watch what Nadella did on the Microsoft earnings call tonight. An analyst asked how Microsoft benefits from enterprises adopting open models when it carries all that frontier lab exposure. Instead of defending the lab relationship, Nadella laid out an architecture: "You've got to keep your harness separate from the model. The harness will ensure that your memory, your context, all of that is external. That means any given model at any given time is swappable." And then the part that should worry anyone underwriting model moats: use frontier models where they earn it, low-cost models where they don't, "and in fact, train your own model when you don't want to use any external model itself because after all, you have all the outputs, you have all the traces, you have all the context." The firm keeps the harness. The models compete for slots inside it. Jensen Huang said most companies will be built on harnesses at the LangChain fireside on July 8. I published the full framework on July 12, five launches in three days, all converging on the same architecture. Tonight the largest enterprise software company on earth made it the official pitch on an earnings call. The moat question in enterprise AI just moved from who has the best weights to who owns the loop around them. And if the completed task is the unit everyone now competes on, someone has to price it for the buyer. That is the next thing we are building at BEP Research: a cost per task tool for enterprises. More on that soon. I also took the paywall off the full framework piece tonight, so the whole thing is free to read:

Ben Pouladian

53,276 просмотров • 18 дней назад

The Never Ending Lore of Harness w/Viv⚡️ Viv brought some amazing perspective around harness design, evals, file systems, RL Envs and so much. 0:00:00 - INTRO 0:03:30 - PhD at Temple University 0:12:42 - Lockheed Martin and MeekMill lore 0:16:18 - Building at LangChain, DeepAgents, R&D in Open Source 0:25:09 - Secret behind Harness Design, Filesystem as most Foundational Harness Primitive 0:42:25 - Trajectories for Continual Learning, Where and Where "NOT to" RL, Skills and Context Rot 0:56:30 - Harness Engineering: OpenClaw and Hermes, Why you might don't need a Claw, Custom Harnesses, Quick Fire (Nick Khami lore) 01:12:15 - Meta-Harness, Self-Improvement Loop, Simulation-as-a-Service, RL Envs (Computer-Use, Long-horizon) 01:28:30 - Advice to anyone 20yo / starting out college
1:33:24

The Never Ending Lore of Harness w/Viv⚡️ Viv brought some amazing perspective around harness design, evals, file systems, RL Envs and so much. 0:00:00 - INTRO 0:03:30 - PhD at Temple University 0:12:42 - Lockheed Martin and MeekMill lore 0:16:18 - Building at LangChain, DeepAgents, R&D in Open Source 0:25:09 - Secret behind Harness Design, Filesystem as most Foundational Harness Primitive 0:42:25 - Trajectories for Continual Learning, Where and Where "NOT to" RL, Skills and Context Rot 0:56:30 - Harness Engineering: OpenClaw and Hermes, Why you might don't need a Claw, Custom Harnesses, Quick Fire (Nick Khami lore) 01:12:15 - Meta-Harness, Self-Improvement Loop, Simulation-as-a-Service, RL Envs (Computer-Use, Long-horizon) 01:28:30 - Advice to anyone 20yo / starting out college

himanshu

31,636 просмотров • 3 месяцев назад

Perplexity CEO Aravind Srinivas on the brutal truth about who actually makes money in AI (and why it's not who you think): Aravind argues that the real value in AI comes from orchestration. He points to products like Codex, Claude Code, and Perplexity Computer: "What is that? It's an orchestration system. It takes a model, pairs it with an agent harness." And what is an agent harness? "The simplest way of describing it is like rules for how the agent loop should run. What are all the skills and sub-agents and connectors and tools it accesses? Without the harness, you don't necessarily capture and convert the intrinsic intelligence in the model into valuable output tokens." This leads to a blunt conclusion about who has a real business in AI, and who doesn't: "If you're literally just a reseller of model tokens, you have no business, because the model will get commoditized. So even if you're a model builder, you don't have a business. As an infra layer, you have some business on serving those output tokens. But as an application layer or model builder, you don't really have a business if you're just a reseller of tokens that come directly out of the model." So where does the value accrue? "You have a business if you know how to take the model, ground it in valuable context, orchestrate it with a really good agent harness, connected to the right set of tools and connectors (whether it's personal connectors or business connectors) and provide the experience to people in one single unified system." Aravind Srinivas then explains Perplexity's specific edge: Beyond orchestrating across tools, files, and connectors, they also orchestrate across models. "That is the differentiation that Anthropic and OpenAI cannot claim, because you wouldn't find GPT-5 inside the Claude Code harness. You wouldn't find Claude Opus inside the Codex harness. These are competing with each other. Whereas you would find both these models inside Perplexity Computer." Why does this matter? Because it all comes down to power. In Aravind's framing, the fundamental cost driver in AI is watts (the one input nobody can subsidize except the government). "Whoever provides the most valuable output tokens with the least amount of power expended to produce them generates the greatest value to the end user, has the most pricing power, has the most value. That is the orchestration problem to solve." His conclusion: "The one single most important metric in AI is token value per watt per user."
2:50

Perplexity CEO Aravind Srinivas on the brutal truth about who actually makes money in AI (and why it's not who you think): Aravind argues that the real value in AI comes from orchestration. He points to products like Codex, Claude Code, and Perplexity Computer: "What is that? It's an orchestration system. It takes a model, pairs it with an agent harness." And what is an agent harness? "The simplest way of describing it is like rules for how the agent loop should run. What are all the skills and sub-agents and connectors and tools it accesses? Without the harness, you don't necessarily capture and convert the intrinsic intelligence in the model into valuable output tokens." This leads to a blunt conclusion about who has a real business in AI, and who doesn't: "If you're literally just a reseller of model tokens, you have no business, because the model will get commoditized. So even if you're a model builder, you don't have a business. As an infra layer, you have some business on serving those output tokens. But as an application layer or model builder, you don't really have a business if you're just a reseller of tokens that come directly out of the model." So where does the value accrue? "You have a business if you know how to take the model, ground it in valuable context, orchestrate it with a really good agent harness, connected to the right set of tools and connectors (whether it's personal connectors or business connectors) and provide the experience to people in one single unified system." Aravind Srinivas then explains Perplexity's specific edge: Beyond orchestrating across tools, files, and connectors, they also orchestrate across models. "That is the differentiation that Anthropic and OpenAI cannot claim, because you wouldn't find GPT-5 inside the Claude Code harness. You wouldn't find Claude Opus inside the Codex harness. These are competing with each other. Whereas you would find both these models inside Perplexity Computer." Why does this matter? Because it all comes down to power. In Aravind's framing, the fundamental cost driver in AI is watts (the one input nobody can subsidize except the government). "Whoever provides the most valuable output tokens with the least amount of power expended to produce them generates the greatest value to the end user, has the most pricing power, has the most value. That is the orchestration problem to solve." His conclusion: "The one single most important metric in AI is token value per watt per user."

Big Brain AI

41,775 просмотров • 13 дней назад

introducing OpenBench v1, an open framework for measuring AI performance and efficiency for your codebase and use case. Companies are realizing that you can't simply tokenmaxx, and are frantically looking for better ways to use and measure AI use and efficiency. One approach is evidenced by the rise in model routers: OpenRouter, Cloudflare, Databricks, Vercel, and now Ramp to name a few. But they'll also need the ability to evaluate how agents are performing in their actual use cases and codebase. A good example is DoorDash's recent evals on their codebase and prs. This will become even more important as companies explore different model + harness combinations. OpenBench will be built to this direction, focusing on the cross between correctness vs efficiency in both token use and latency. Starting off, OpenBench makes it easy for anyone to add to the task set, and run a variety of harness + models. The framework also makes it easy to add any custom harness variant, for example I've been testing codex variants with ablations against the stock codex harness. OpenBench will also have tooling to help with discovering/adding reliable tasks from your repo. Today I have integrated harnesses: codex, claude, cursor, devin, grok build, pi, and eval'ed them for different models like gpt 5.6-sol, GLM 5.2, Kimi K3, Grok 4.5, etc. measuring correctness %, token use (in/out/cache), and latency.
0:20

introducing OpenBench v1, an open framework for measuring AI performance and efficiency for your codebase and use case. Companies are realizing that you can't simply tokenmaxx, and are frantically looking for better ways to use and measure AI use and efficiency. One approach is evidenced by the rise in model routers: OpenRouter, Cloudflare, Databricks, Vercel, and now Ramp to name a few. But they'll also need the ability to evaluate how agents are performing in their actual use cases and codebase. A good example is DoorDash's recent evals on their codebase and prs. This will become even more important as companies explore different model + harness combinations. OpenBench will be built to this direction, focusing on the cross between correctness vs efficiency in both token use and latency. Starting off, OpenBench makes it easy for anyone to add to the task set, and run a variety of harness + models. The framework also makes it easy to add any custom harness variant, for example I've been testing codex variants with ablations against the stock codex harness. OpenBench will also have tooling to help with discovering/adding reliable tasks from your repo. Today I have integrated harnesses: codex, claude, cursor, devin, grok build, pi, and eval'ed them for different models like gpt 5.6-sol, GLM 5.2, Kimi K3, Grok 4.5, etc. measuring correctness %, token use (in/out/cache), and latency.

Matthew Lam

121,718 просмотров • 26 дней назад

EVERYTHING you NEED to know about Jack Dorsey's AI agent "Slack killer" Buzz (set up, use-cases etc in 38 mins) What we get into: 1. What Buzz actually is and should founders switch from Slack? 2. How to swap the model under any agent and keep all your context? 3. How to talk to your agents live with audio huddles? 4. How to get agents to build and deploy real apps for you, like a full CRM from one ask? 5. How to set up the context loop that feeds your live app data back to your agents? 6. How to share compute so a few people split one machine running a local model? 7. Who it's actually for right now, and what's still rough? Full breakdown on the pod The Startup Ideas Podcast (SIP) 🧃. Thanks to Vinny for jumping on and clearly explaining jack and team's latest product. My TLDR take is Buzz is a glimpse into the future of work. Some of you will roll your eyes at that, and I get it, it's alpha software and it's slow in places. But the core idea, that your context is the foundation and agents build out from there, is right, and that's worth seeing early. Watch Curious what you think
38:43

EVERYTHING you NEED to know about Jack Dorsey's AI agent "Slack killer" Buzz (set up, use-cases etc in 38 mins) What we get into: 1. What Buzz actually is and should founders switch from Slack? 2. How to swap the model under any agent and keep all your context? 3. How to talk to your agents live with audio huddles? 4. How to get agents to build and deploy real apps for you, like a full CRM from one ask? 5. How to set up the context loop that feeds your live app data back to your agents? 6. How to share compute so a few people split one machine running a local model? 7. Who it's actually for right now, and what's still rough? Full breakdown on the pod The Startup Ideas Podcast (SIP) 🧃. Thanks to Vinny for jumping on and clearly explaining jack and team's latest product. My TLDR take is Buzz is a glimpse into the future of work. Some of you will roll your eyes at that, and I get it, it's alpha software and it's slow in places. But the core idea, that your context is the foundation and agents build out from there, is right, and that's worth seeing early. Watch Curious what you think

GREG ISENBERG

551,065 просмотров • 19 дней назад

The entire AI industry is racing to build the smartest model. Satya Nadella just admitted that is not where the money is. The model is not the product. The harness is. That is the exact line. And it changes what Microsoft is actually competing on. OpenAI, Anthropic, Google, xAI, Meta every frontier lab is pouring hundreds of billions into training compute, chasing the next capability jump. Each betting that raw model intelligence is the moat. Microsoft is doing the opposite. It is building the harness the orchestration layer that sits above the model, connecting it to tools, data, permissions, sub-agents, and enterprise workflows. And it is letting OpenAI, Anthropic, and MAI compete to plug into it. "You need the model. But the model is not the product. The harness is." So do the math on what a harness actually does. A raw model dropped into an enterprise answers questions. That is a chatbot. A harness turns that same model into an agent that reads the SharePoint, edits the ERP entry, pulls the GitHub PR, updates Salesforce, and files the Excel report with the right permissions, the right audit trail, and the right sub-agent for each sub-task. The model provides the intelligence. The harness converts intelligence into work. Now here's where it gets interesting. "Even the best model in the world will feel broken without a great harness. And an okay model with a great harness can feel like magic." If that is true, the enterprise buyer is not buying model quality. The enterprise buyer is buying the harness. Which means model quality becomes a commodity input over time, and harness quality becomes the sustainable moat. Compare that to the strategy the entire frontier lab industry is executing. Everyone else is chasing the numerator raw intelligence. Almost nobody at scale is racing to build the denominator the orchestration layer that determines whether that intelligence can actually be deployed profitably inside a real company. The frontier model race has a 10 to 20 percent chance of producing a single dominant winner. Nadella just told the industry he does not need to be that winner. If OpenAI wins, Microsoft wins. If Anthropic wins, Microsoft wins. If MAI wins, Microsoft wins. If someone Microsoft has never heard of trains a better model in 2027, Microsoft still wins. Because the compute they train on, the harness they get plugged into, the enterprise contracts they get delivered through, and the products they sit inside are all Microsoft. He is not building the best AI model. He is building the layer that the best AI model has to run on to make anyone money. I wonder which position looks more valuable in ten years.
3:19

The entire AI industry is racing to build the smartest model. Satya Nadella just admitted that is not where the money is. The model is not the product. The harness is. That is the exact line. And it changes what Microsoft is actually competing on. OpenAI, Anthropic, Google, xAI, Meta every frontier lab is pouring hundreds of billions into training compute, chasing the next capability jump. Each betting that raw model intelligence is the moat. Microsoft is doing the opposite. It is building the harness the orchestration layer that sits above the model, connecting it to tools, data, permissions, sub-agents, and enterprise workflows. And it is letting OpenAI, Anthropic, and MAI compete to plug into it. "You need the model. But the model is not the product. The harness is." So do the math on what a harness actually does. A raw model dropped into an enterprise answers questions. That is a chatbot. A harness turns that same model into an agent that reads the SharePoint, edits the ERP entry, pulls the GitHub PR, updates Salesforce, and files the Excel report with the right permissions, the right audit trail, and the right sub-agent for each sub-task. The model provides the intelligence. The harness converts intelligence into work. Now here's where it gets interesting. "Even the best model in the world will feel broken without a great harness. And an okay model with a great harness can feel like magic." If that is true, the enterprise buyer is not buying model quality. The enterprise buyer is buying the harness. Which means model quality becomes a commodity input over time, and harness quality becomes the sustainable moat. Compare that to the strategy the entire frontier lab industry is executing. Everyone else is chasing the numerator raw intelligence. Almost nobody at scale is racing to build the denominator the orchestration layer that determines whether that intelligence can actually be deployed profitably inside a real company. The frontier model race has a 10 to 20 percent chance of producing a single dominant winner. Nadella just told the industry he does not need to be that winner. If OpenAI wins, Microsoft wins. If Anthropic wins, Microsoft wins. If MAI wins, Microsoft wins. If someone Microsoft has never heard of trains a better model in 2027, Microsoft still wins. Because the compute they train on, the harness they get plugged into, the enterprise contracts they get delivered through, and the products they sit inside are all Microsoft. He is not building the best AI model. He is building the layer that the best AI model has to run on to make anyone money. I wonder which position looks more valuable in ten years.

Vikram M

21,463 просмотров • 1 месяц назад

Anthropic engineer: "Harness engineering is a really rare skill right now - and it's hard to know if you're even good at it." how he actually thinks about building the full system: • step 1 → the model. already smarter than we use it. "freeze development - you'd find new capabilities for another 6-12 months" • step 2 → the harness. delete the steering. "we stopped using plan mode - the model thinks correctly" • step 3 → the agents. workflows let Claude build its own harness per task and spin sub-agents. what didn't fit in one context window now runs across many • step 4 → the context. "RAG is an anti-pattern. use grep." memory via files, clean context window, prompt caching. that's the stack most people optimize step 1. he optimizes all four. Watch the full video, then read the guide below on how to build an agentic system.
46:31

Anthropic engineer: "Harness engineering is a really rare skill right now - and it's hard to know if you're even good at it." how he actually thinks about building the full system: • step 1 → the model. already smarter than we use it. "freeze development - you'd find new capabilities for another 6-12 months" • step 2 → the harness. delete the steering. "we stopped using plan mode - the model thinks correctly" • step 3 → the agents. workflows let Claude build its own harness per task and spin sub-agents. what didn't fit in one context window now runs across many • step 4 → the context. "RAG is an anti-pattern. use grep." memory via files, clean context window, prompt caching. that's the stack most people optimize step 1. he optimizes all four. Watch the full video, then read the guide below on how to build an agentic system.

Codez

43,789 просмотров • 1 месяц назад

When Mudith Jayasekara and I met Gabe Pereyra, we were expecting just another vanilla intro call and instead had the best yarn about research, the state of LLMs, and where intelligence is actually heading. It's rare to meet a founder this deep in the weeds who's also building for one of the most important verticals in this new age of intelligence So it was awesome to sit down with Gabe for an extended discussion on what it take to build agents that can reliably complete work over hours, days, or even longer? We talked about why agents today struggle with search and long context windows and how techniques like KV-cache compaction, synthetic data, and continual learning could help. 0:00 Introduction 0:36 Getting legal agents to review the whole data room 2:08 Data rooms larger than any context window 5:28 How far open-source models can go 7:58 Where specialist models fit in legal AI 10:59 Training legal models when client data is off-limits 13:06 Teaching a model how a law firm works 13:59 What belongs in context vs. model weights 15:36 From firm-wide AI to a model for every lawyer 18:37 What training adds beyond retrieving the right cases 20:26 Why context windows have plateaued 24:01 How models could learn continuously on the job 26:12 Can AI recursively improve AI research? 27:07 Research agents can run experiments but not choose them 30:00 Why open-ended research is hard to train 33:47 Why deployment, not intelligence, is the bottleneck 35:08 The cost of frontier intelligence 36:59 Different neolabs, different paths to intelligence 39:26 Using open datasets to compare research methods 41:13 Conclusion
41:50

When Mudith Jayasekara and I met Gabe Pereyra, we were expecting just another vanilla intro call and instead had the best yarn about research, the state of LLMs, and where intelligence is actually heading. It's rare to meet a founder this deep in the weeds who's also building for one of the most important verticals in this new age of intelligence So it was awesome to sit down with Gabe for an extended discussion on what it take to build agents that can reliably complete work over hours, days, or even longer? We talked about why agents today struggle with search and long context windows and how techniques like KV-cache compaction, synthetic data, and continual learning could help. 0:00 Introduction 0:36 Getting legal agents to review the whole data room 2:08 Data rooms larger than any context window 5:28 How far open-source models can go 7:58 Where specialist models fit in legal AI 10:59 Training legal models when client data is off-limits 13:06 Teaching a model how a law firm works 13:59 What belongs in context vs. model weights 15:36 From firm-wide AI to a model for every lawyer 18:37 What training adds beyond retrieving the right cases 20:26 Why context windows have plateaued 24:01 How models could learn continuously on the job 26:12 Can AI recursively improve AI research? 27:07 Research agents can run experiments but not choose them 30:00 Why open-ended research is hard to train 33:47 Why deployment, not intelligence, is the bottleneck 35:08 The cost of frontier intelligence 36:59 Different neolabs, different paths to intelligence 39:26 Using open datasets to compare research methods 41:13 Conclusion

Charlie O'Neill

91,088 просмотров • 25 дней назад

Today's AI models train once. We don't work that way. We learn continuously, forget what doesn't matter, and retain what does. That gap is what Dan Biderman and Jessy Lin are closing at Engram. AI that never stops learning, with memory that lives inside the model instead of bolted on as an afterthought. In our latest Training Data episode we get into why memory is the next frontier: why the brain forgets on purpose, why RAG is a band-aid, and what becomes possible when a model is always training. 00:00 Introduction 00:59 Always Training Explained 01:51 Beyond Context Windows 03:29 Ngram Product Overview 04:34 Adapters And Training Signals 05:32 Internalize Vs Externalize 06:49 Compute And Token Savings 08:19 Teams First Then Individuals 08:51 Memorization Vs Understanding 12:47 Dreams And Offline Digestion 14:08 Training Beats Curation 15:19 Why Everyone Needs A Model 21:44 Bitter Lesson And Architecture 24:44 RAG Killer And KV Cache 31:38 Future Of Memory And Models
44:51

Today's AI models train once. We don't work that way. We learn continuously, forget what doesn't matter, and retain what does. That gap is what Dan Biderman and Jessy Lin are closing at Engram. AI that never stops learning, with memory that lives inside the model instead of bolted on as an afterthought. In our latest Training Data episode we get into why memory is the next frontier: why the brain forgets on purpose, why RAG is a band-aid, and what becomes possible when a model is always training. 00:00 Introduction 00:59 Always Training Explained 01:51 Beyond Context Windows 03:29 Ngram Product Overview 04:34 Adapters And Training Signals 05:32 Internalize Vs Externalize 06:49 Compute And Token Savings 08:19 Teams First Then Individuals 08:51 Memorization Vs Understanding 12:47 Dreams And Offline Digestion 14:08 Training Beats Curation 15:19 Why Everyone Needs A Model 21:44 Bitter Lesson And Architecture 24:44 RAG Killer And KV Cache 31:38 Future Of Memory And Models

Sequoia Capital

83,323 просмотров • 1 месяц назад