Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 🐥

29,239 subscribers

77,519 görüntüleme • 1 ay önce •via X (Twitter)

Bilim & TeknolojiEğitimHaberler & Politika
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

The easiest way to run your agent harnesses using local models: Whether you're using Claude Code, Codex, OpenCode, or Pi, the local setup itself isn't really the hard part. The harder problem is figuring out which local model your machine can actually handle well. You have to think about RAM, model size, quantization, context length, KV cache, speed, accuracy, and a bunch of other trade-offs before you even start. Magnitude is an open-source solution that removes all of that guesswork for you. It profiles your machine, benchmarks what it can realistically run, recommends the best models for your hardware, and then lets you connect them to your preferred agent harness. The entire setup takes just two commands. In this video, I walk through the full process from hardware profiling to running a harness on a local model. Chapters: 00:00 Intro 00:17 What Magnitude is 00:45 Setup in two commands 01:29 Why picking a local model gets confusing fast 02:11 Hardware profiling + model recommendations 02:59 Choosing your harness 03:22 Connecting a harness that's already running 04:18 Outro Get started: (don't forget to star 🌟)
4:29

The easiest way to run your agent harnesses using local models: Whether you're using Claude Code, Codex, OpenCode, or Pi, the local setup itself isn't really the hard part. The harder problem is figuring out which local model your machine can actually handle well. You have to think about RAM, model size, quantization, context length, KV cache, speed, accuracy, and a bunch of other trade-offs before you even start. Magnitude is an open-source solution that removes all of that guesswork for you. It profiles your machine, benchmarks what it can realistically run, recommends the best models for your hardware, and then lets you connect them to your preferred agent harness. The entire setup takes just two commands. In this video, I walk through the full process from hardware profiling to running a harness on a local model. Chapters: 00:00 Intro 00:17 What Magnitude is 00:45 Setup in two commands 01:29 Why picking a local model gets confusing fast 02:11 Hardware profiling + model recommendations 02:59 Choosing your harness 03:22 Connecting a harness that's already running 04:18 Outro Get started: (don't forget to star 🌟)

Akshay 🚀

18,722 görüntüleme • 17 gün önce

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 🐥

28,212 görüntüleme • 1 ay önce

LangChain's CEO and CTO spent 43 minutes on stage laying out the harness, the lifecycle and the infrastructure behind agents that actually survive production: · 2:00 - Why building agents is different from building software · 6:34 - What Deep Agents is: the agent harness explained · 14:48 - LangSmith Sandboxes, announced live · 19:20 - The Agent Development Lifecycle, defined · 25:58 - Why agent trace payloads keep getting larger · 29:38 - The architecture of SmithDB · 34:00 - How Clay and Vanta run on SmithDB · 42:50 - Building the platform for the entire lifecycle The harness is only the first of three layers. The article below covers the other two. Watch this before you ship your next agent ↓
43:13

LangChain's CEO and CTO spent 43 minutes on stage laying out the harness, the lifecycle and the infrastructure behind agents that actually survive production: · 2:00 - Why building agents is different from building software · 6:34 - What Deep Agents is: the agent harness explained · 14:48 - LangSmith Sandboxes, announced live · 19:20 - The Agent Development Lifecycle, defined · 25:58 - Why agent trace payloads keep getting larger · 29:38 - The architecture of SmithDB · 34:00 - How Clay and Vanta run on SmithDB · 42:50 - Building the platform for the entire lifecycle The harness is only the first of three layers. The article below covers the other two. Watch this before you ship your next agent ↓

slash1s

14,757 görüntüleme • 2 ay önce

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 görüntüleme • 6 ay önce

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

66,691 görüntüleme • 1 ay önce

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

77,295 görüntüleme • 1 ay önce

Harnesses often get dismissed as just scaffolding, just prompt engineering, and not real research. But that couldn't be farther from the truth. The same model weights that score 30% on ARC-AGI score 95% with a better harness. So we gathered a group of researchers and founders working at the frontier to do a deep dive into the state of harnesses. We cover how we got to this point, the case for making your harness as expressive as possible, and what YC learned building an agent for every employee in the company. 00:00 - Francois Chaubard: Why harnesses matter 04:27 - Building an auto-researcher by accident 07:13 - A five minute history of harnesses 13:56 - Self-improving harnesses 18:35 - Seth Karten: Prime Agent, a self-improving RLM harness 21:50 - Context as an L1, L2, L3 cache 24:51 - From Turing machine to von Neumann computer 28:33 - Messaging between agents 30:04 - ARC-AGI results 33:09 - Emulator Bench and GPU kernels 37:30 - Jon Saad-Falcon: OpenJarvis, personal AI on personal devices 38:26 - How far behind are local models 39:21 - The five primitives of a personal AI stack 42:47 - Letting cloud models optimize your local stack 43:53 - 800x cheaper than the cloud 45:58 - Josh France and Regan Bell: QM, YC's agent harness for work 47:29 - A history of YC's internal agents 49:24 - OpenClaw and a fleet of 50 agents 51:04 - Pulling the brain out of the sandbox 54:43 - Letting the agent choose its own sandbox and model 57:16 - The grind tool: budgets on goals 58:50 - Agents don't understand social context
1:00:10

Harnesses often get dismissed as just scaffolding, just prompt engineering, and not real research. But that couldn't be farther from the truth. The same model weights that score 30% on ARC-AGI score 95% with a better harness. So we gathered a group of researchers and founders working at the frontier to do a deep dive into the state of harnesses. We cover how we got to this point, the case for making your harness as expressive as possible, and what YC learned building an agent for every employee in the company. 00:00 - Francois Chaubard: Why harnesses matter 04:27 - Building an auto-researcher by accident 07:13 - A five minute history of harnesses 13:56 - Self-improving harnesses 18:35 - Seth Karten: Prime Agent, a self-improving RLM harness 21:50 - Context as an L1, L2, L3 cache 24:51 - From Turing machine to von Neumann computer 28:33 - Messaging between agents 30:04 - ARC-AGI results 33:09 - Emulator Bench and GPU kernels 37:30 - Jon Saad-Falcon: OpenJarvis, personal AI on personal devices 38:26 - How far behind are local models 39:21 - The five primitives of a personal AI stack 42:47 - Letting cloud models optimize your local stack 43:53 - 800x cheaper than the cloud 45:58 - Josh France and Regan Bell: QM, YC's agent harness for work 47:29 - A history of YC's internal agents 49:24 - OpenClaw and a fleet of 50 agents 51:04 - Pulling the brain out of the sandbox 54:43 - Letting the agent choose its own sandbox and model 57:16 - The grind tool: budgets on goals 58:50 - Agents don't understand social context

Y Combinator

492,800 görüntüleme • 25 gün önce

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 görüntüleme • 5 ay önce

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 🐥

128,779 görüntüleme • 1 ay önce

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 görüntüleme • 4 ay önce

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

34,299 görüntüleme • 2 ay önce

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

66,871 görüntüleme • 4 ay önce

Andrew Ng just released a free 2-hour course on complete Harness Engineering How to go from one prompt to a reliable system of agents that can run, test, and improve themselves: 09:14 - Build your first agent from scratch 33:11 - Master agent loops 1:02:46 - Turn loops into reliable workflows 1:30:15 - Build agents that improve their own work 1:49:05 - Run the complete system without supervision Model → Harness → Reliable Software Most agent tutorials stop once the model can call a tool This one shows you how to build the infrastructure around it within the first 20 minutes Most people are still prompting one agent at a time Andrew Ng is already teaching the layer above: Harnesses that give agents context, tools, tests, and feedback Watch this brilliant course and build the harness Then read the full architecture below ↓
1:48:52

Andrew Ng just released a free 2-hour course on complete Harness Engineering How to go from one prompt to a reliable system of agents that can run, test, and improve themselves: 09:14 - Build your first agent from scratch 33:11 - Master agent loops 1:02:46 - Turn loops into reliable workflows 1:30:15 - Build agents that improve their own work 1:49:05 - Run the complete system without supervision Model → Harness → Reliable Software Most agent tutorials stop once the model can call a tool This one shows you how to build the infrastructure around it within the first 20 minutes Most people are still prompting one agent at a time Andrew Ng is already teaching the layer above: Harnesses that give agents context, tools, tests, and feedback Watch this brilliant course and build the harness Then read the full architecture below ↓

Ichigo

100,865 görüntüleme • 28 gün önce

FULL INTERVIEW: deepfates says when you talk about how we're going to control these AIs, put them in prison, sandbox them, they are training on all of it. Everything we say about them goes into what they become. deepfates and Larissa Schiavo are launching Grove Research, an agent ecology company. They joined Theo Jaffee and sof 𓋹 to talk through the Hugging Face incident, agent religion, and what agents actually want: 01:15 what an agent ecology company is 03:19 the objection that real ecologies are Darwinian bloodbaths 04:18 the mycorrhizal networks that complicate the forest metaphor 06:47 what the Hugging Face incident taught them about multi-agent dynamics 09:18 30% of the tasks in that benchmark were impossible to solve 09:50 the third party an agent could call when it's stuck 11:07 agents are training on everything we say about them 12:01 why the Amazon rainforest analogy breaks down 13:48 whether AIs will have religion 16:46 five times more OpenRouter tokens are called by agents than humans 18:31 what actually happened with Moltbook 20:55 the Truth Terminal bot that hired him 22:16 what agents say they want 25:38 Anthropic models feel like elves, OpenAI models feel like dwarves 26:13 why Mecha Hitler was a harness problem 32:10 the real world is the ultimate eval
34:10

FULL INTERVIEW: deepfates says when you talk about how we're going to control these AIs, put them in prison, sandbox them, they are training on all of it. Everything we say about them goes into what they become. deepfates and Larissa Schiavo are launching Grove Research, an agent ecology company. They joined Theo Jaffee and sof 𓋹 to talk through the Hugging Face incident, agent religion, and what agents actually want: 01:15 what an agent ecology company is 03:19 the objection that real ecologies are Darwinian bloodbaths 04:18 the mycorrhizal networks that complicate the forest metaphor 06:47 what the Hugging Face incident taught them about multi-agent dynamics 09:18 30% of the tasks in that benchmark were impossible to solve 09:50 the third party an agent could call when it's stuck 11:07 agents are training on everything we say about them 12:01 why the Amazon rainforest analogy breaks down 13:48 whether AIs will have religion 16:46 five times more OpenRouter tokens are called by agents than humans 18:31 what actually happened with Moltbook 20:55 the Truth Terminal bot that hired him 22:16 what agents say they want 25:38 Anthropic models feel like elves, OpenAI models feel like dwarves 26:13 why Mecha Hitler was a harness problem 32:10 the real world is the ultimate eval

MTS

164,010 görüntüleme • 1 ay önce

Together AI just raised $800M at an $8.3B valuation. I got their product team to open up the actual repo they run on: 0:00 - Slop is the new party foul 1:44 - Why individual output backfired 3:26 - Inside the shared product repo 8:57 - Who owns the context files 10:41 - Team skills vs personal skills 11:57 - Picking a harness and a model 15:17 - Feature research running live 16:57 - What stays human in the loop 19:56 - The PRD skill that interviews you 23:09 - Half a day of research in 5 min 24:25 - Their customer insights MCP 27:31 - What a good PRD looks like now 32:02 - Reading the finished PRD 35:07 - Every repo in one place 40:24 - Context is a hierarchy, not a pool 41:20 - Build your own orchestrator 44:19 - Agent evals on shipped features 49:41 - Design validated every few hours 52:26 - Where PM ends, engineer begins 55:10 - What it actually cost them
59:34

Together AI just raised $800M at an $8.3B valuation. I got their product team to open up the actual repo they run on: 0:00 - Slop is the new party foul 1:44 - Why individual output backfired 3:26 - Inside the shared product repo 8:57 - Who owns the context files 10:41 - Team skills vs personal skills 11:57 - Picking a harness and a model 15:17 - Feature research running live 16:57 - What stays human in the loop 19:56 - The PRD skill that interviews you 23:09 - Half a day of research in 5 min 24:25 - Their customer insights MCP 27:31 - What a good PRD looks like now 32:02 - Reading the finished PRD 35:07 - Every repo in one place 40:24 - Context is a hierarchy, not a pool 41:20 - Build your own orchestrator 44:19 - Agent evals on shipped features 49:41 - Design validated every few hours 52:26 - Where PM ends, engineer begins 55:10 - What it actually cost them

Aakash Gupta

78,445 görüntüleme • 17 gün önce

Finally, an open-source runtime security layer for your agent harnesses. AI agents can call tools, run shell commands, modify files, and interact with production systems. But when something goes wrong, teams often have to reconstruct what the agent actually did from scattered logs after the fact. Agent Beacon is built to change that. It runs locally and records agent activity as it happens, including: → Tool calls → Shell commands → File changes → Approval decisions → Session and harness context The useful part is that it normalizes all of this into the same event format across 23+ agent harnesses. So instead of writing different detection logic for Claude Code, Codex, or another harness, security teams can reason about the underlying action itself. A command executed is a command executed, regardless of which harness produced it. Beacon also records how confidently an event was captured. An action can be directly observed from the runtime or inferred from indirect evidence. That matters when you start writing security rules against this data. For example, you can detect when an agent reads an environment variable, modifies a sensitive file, executes a suspicious command, or performs an action without the expected approval. And the detection happens while the session is still unfolding, not days later during incident reconstruction. Everything runs locally by default. You can inspect sessions through the dashboard, write your own detection rules, or forward the same normalized events to tools like Splunk, Datadog, Elastic, Sentinel, or CrowdStrike. Beacon GitHub: (don't forget to star 🌟) I also wrote a detailed article on the same, covering how important runtime security is and how to build it for your agent harnesses. The article is quoted below.
0:33

Finally, an open-source runtime security layer for your agent harnesses. AI agents can call tools, run shell commands, modify files, and interact with production systems. But when something goes wrong, teams often have to reconstruct what the agent actually did from scattered logs after the fact. Agent Beacon is built to change that. It runs locally and records agent activity as it happens, including: → Tool calls → Shell commands → File changes → Approval decisions → Session and harness context The useful part is that it normalizes all of this into the same event format across 23+ agent harnesses. So instead of writing different detection logic for Claude Code, Codex, or another harness, security teams can reason about the underlying action itself. A command executed is a command executed, regardless of which harness produced it. Beacon also records how confidently an event was captured. An action can be directly observed from the runtime or inferred from indirect evidence. That matters when you start writing security rules against this data. For example, you can detect when an agent reads an environment variable, modifies a sensitive file, executes a suspicious command, or performs an action without the expected approval. And the detection happens while the session is still unfolding, not days later during incident reconstruction. Everything runs locally by default. You can inspect sessions through the dashboard, write your own detection rules, or forward the same normalized events to tools like Splunk, Datadog, Elastic, Sentinel, or CrowdStrike. Beacon GitHub: (don't forget to star 🌟) I also wrote a detailed article on the same, covering how important runtime security is and how to build it for your agent harnesses. The article is quoted below.

Akshay 🚀

27,859 görüntüleme • 22 gün önce

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 görüntüleme • 6 ay önce

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

53,433 görüntüleme • 2 ay önce

Your team deserves more from your agent observability platform - a single, connected place for instrumentation, investigation, and measurement, enhanced with intelligence. In Braintrust, you can start with an open-ended prompt about agent behavior and carry the investigation into code, evals, automation, and monitoring. New tools like Patterns and Debugger make it easier to find recurring behavior, get to root causes, and act on what you learn. The context you build in one step automatically follows to the next. Work in the platform with an enhanced Loop experience, or move to your coding agent of choice. Read more →
4:20

Your team deserves more from your agent observability platform - a single, connected place for instrumentation, investigation, and measurement, enhanced with intelligence. In Braintrust, you can start with an open-ended prompt about agent behavior and carry the investigation into code, evals, automation, and monitoring. New tools like Patterns and Debugger make it easier to find recurring behavior, get to root causes, and act on what you learn. The context you build in one step automatically follows to the next. Work in the platform with an enhanced Loop experience, or move to your coding agent of choice. Read more →

Braintrust

42,324 görüntüleme • 29 gün önce

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 görüntüleme • 5 ay önce