Loading video...

Video Failed to Load

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

OpenAI's New Agent Stack: Superhuman Computer Use, Dots, Decisions API, UltraFast, & the AI Cloud OpenAI’s Ari Weinstein and Nikunj Handa explain why Computer Use is already becoming faster than humans at real-world tasks, how Dots gives agents their own cloud computers, why better models can now debug and... show more

Latent.Space

33,168 subscribers

24,541 views • 2 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

6 Comments

Kizuno182 days ago

@OpenAI @AriX @nikunjhanda superhuman computer use speed only matters if action execution is coupled to accessibility tree state: raw coordinate clicks miss dynamic elements under fast renders. in our autonomous pipeline, executing actions against accessibility nodes keeps computer use 100% synchronized

Forge Orbital Inc2 days ago

@OpenAI @AriX @nikunjhanda Agent stacks keep getting more capable. The question regulated buyers ask next: what was this agent allowed to do, and can we prove it later? We built Forge for that: signed, replayable records on your own hardware. Would love to talk it through on the show.

Nikhil2 days ago

@OpenAI @AriX @nikunjhanda Dots versus Grok Bot versus Metamuse. Is gonna win?

EKOS _ AGI 🇮🇷2 days ago

The interesting part isn’t just that agents can now operate faster and recover from failures. It’s the amount of execution history this creates. Decisions, tool calls, failures, recoveries and verified outcomes can become a compounding advantage if they’re preserved as reusable knowledge. Otherwise every faster agent is still starting from zero. Do you agree? @sama

Oleg2 days ago

@OpenAI @AriX @nikunjhanda my agents drive a real chrome. half their rules exist to slow them down

TobiasDev 🇦🇷2 days ago

@OpenAI @AriX @nikunjhanda computer use faster than humans plus agents with their own cloud, the stack talk is getting concrete

Related Videos

At DevDay, OpenAI announced: - Their answer to Muse and Grokbot: Dots (although not free like Muse) - Their answer to Anthropic’s latest models: GPT-6.1-Sol - Their answer to Jev: The decision API They also announced ChatGPT Spaces and Ultrafast mode (at 6x cost) as well as everything being available in the cloud and an agents API (with computer use).

At DevDay, OpenAI announced: - Their answer to Muse and Grokbot: Dots (although not free like Muse) - Their answer to Anthropic’s latest models: GPT-6.1-Sol - Their answer to Jev: The decision API They also announced ChatGPT Spaces and Ultrafast mode (at 6x cost) as well as everything being available in the cloud and an agents API (with computer use).

Matt Wolfe

22,889 views • 4 days ago

Modal's Agent-Native Cloud: DX→AX, sandboxes, elastic inference, and 100,000 rollouts Modal CTO Akshat Bubna explains why developer experience is becoming agent experience, why agents need infra they can operate instead of YAML they have to reason through, how sandboxes turn the agent loop into something real, why elastic inference and GPU snapshotting matter for production AI, how RL rollouts can require 100,000 sandboxes, and why Modal’s $355M Series C marks a new phase for AI-native cloud infrastructure.

Modal's Agent-Native Cloud: DX→AX, sandboxes, elastic inference, and 100,000 rollouts Modal CTO Akshat Bubna explains why developer experience is becoming agent experience, why agents need infra they can operate instead of YAML they have to reason through, how sandboxes turn the agent loop into something real, why elastic inference and GPU snapshotting matter for production AI, how RL rollouts can require 100,000 sandboxes, and why Modal’s $355M Series C marks a new phase for AI-native cloud infrastructure.

Latent.Space

16,308 views • 2 months ago

🎮 Computer Use Agent Arena is LIVE! 🚀 🔥 Easiest way to test computer-use agents in the wild without any setup 🌟 Compare top VLMs: OpenAI Operator, Claude 3.7, Gemini 2.5 Pro, Qwen 2.5 vl and more 🕹️ Test agents on 100+ real apps & webs with one-click config 🔒 Safe & free access on cloud-hosted machines Page: Leaderboard (tentative): Blog: Data & Code (coming soon): ⭐️Why Computer Agent Arena? 1️⃣Beyond Static Benchmarks: We use computers to perform enormous tasks and workflows every day, and AI agents have the potential to automate these tasks. However, existing benchmarks are very limited (e.g., only 369 tasks in OSWorld and 812 tasks in WebArena). To better measure their capabilities, we introduce Computer Agent Arena for users to easily compare & test AI agents on all kinds of crowdsourced real-world computer use tasks. 2️⃣Cloud Testing, Simplified: As agents like OpenAI’s Operator and Claude 3.7 sonnet release, users face configuration challenges and privacy hurdles to deploy on their own computers. Our platform integrates these agents with cloud-hosted machines, providing users with quick and secure access. 3️⃣Unified Embodied Digital Environment: Unlike Chatbot Arena, we provide users with a real embodied environment—computers—where all agents are grounded in real computer tasks and environments. Led by @XLANG_Lab [1/🧵]

🎮 Computer Use Agent Arena is LIVE! 🚀 🔥 Easiest way to test computer-use agents in the wild without any setup 🌟 Compare top VLMs: OpenAI Operator, Claude 3.7, Gemini 2.5 Pro, Qwen 2.5 vl and more 🕹️ Test agents on 100+ real apps & webs with one-click config 🔒 Safe & free access on cloud-hosted machines Page: Leaderboard (tentative): Blog: Data & Code (coming soon): ⭐️Why Computer Agent Arena? 1️⃣Beyond Static Benchmarks: We use computers to perform enormous tasks and workflows every day, and AI agents have the potential to automate these tasks. However, existing benchmarks are very limited (e.g., only 369 tasks in OSWorld and 812 tasks in WebArena). To better measure their capabilities, we introduce Computer Agent Arena for users to easily compare & test AI agents on all kinds of crowdsourced real-world computer use tasks. 2️⃣Cloud Testing, Simplified: As agents like OpenAI’s Operator and Claude 3.7 sonnet release, users face configuration challenges and privacy hurdles to deploy on their own computers. Our platform integrates these agents with cloud-hosted machines, providing users with quick and secure access. 3️⃣Unified Embodied Digital Environment: Unlike Chatbot Arena, we provide users with a real embodied environment—computers—where all agents are grounded in real computer tasks and environments. Led by @XLANG_Lab [1/🧵]

Bowen Wang

93,273 views • 1 year ago

I used my codex reset to cut this OpenAI Dev Day recap, where I cover my favorite releases for the day (spoiler alert: I'm now an expensive Ultrafast girl) What I cover: (00:58) Dots: early impressions and rough edges (06:57) Spaces: working with humans and agents (10:37) Sites, connectors, and sharing internal tools (13:06) Models and platform: GPT-6.1 Sol (14:36) Decisions API: fast decisions with vision (17:17) Astra ultrafast: speed, pricing, and possibilities (22:25) Agents API, computer use, plugins, and plan updates (23:03) What I’d try first Full ep on YT:

I used my codex reset to cut this OpenAI Dev Day recap, where I cover my favorite releases for the day (spoiler alert: I'm now an expensive Ultrafast girl) What I cover: (00:58) Dots: early impressions and rough edges (06:57) Spaces: working with humans and agents (10:37) Sites, connectors, and sharing internal tools (13:06) Models and platform: GPT-6.1 Sol (14:36) Decisions API: fast decisions with vision (17:17) Astra ultrafast: speed, pricing, and possibilities (22:25) Agents API, computer use, plugins, and plan updates (23:03) What I’d try first Full ep on YT:

claire vo 🖤

11,651 views • 3 days ago

🆕The Age of Async Agents: Devin’s 7x PR growth, 80% AI commits, background agents, memory, testing, & Open-Inspect Cognition cofounder + CPO Walden and Open-Inspect creator explain why engineering is moving from local IDEs to cloud background agents, how Devin went from 16% to 80% of commits across Cognition repos, why spec-to-PR workflows became real after the December model inflection, why testing is harder than computer use, how Devin separates the brain from the machine, why MCP is not enough for production agent integrations, and how PMs, support teams, and SRE workflows are starting to turn Slack messages into pull requests.

🆕The Age of Async Agents: Devin’s 7x PR growth, 80% AI commits, background agents, memory, testing, & Open-Inspect Cognition cofounder + CPO Walden and Open-Inspect creator explain why engineering is moving from local IDEs to cloud background agents, how Devin went from 16% to 80% of commits across Cognition repos, why spec-to-PR workflows became real after the December model inflection, why testing is harder than computer use, how Devin separates the brain from the machine, why MCP is not enough for production agent integrations, and how PMs, support teams, and SRE workflows are starting to turn Slack messages into pull requests.

Latent.Space

24,685 views • 4 months ago

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

Philipp Schmid

21,769 views • 4 months ago

🆕Daytona’s Agent-Native Compute: 60ms sandboxes, 50K startups in 75 sec, 850K daily runs, RL/evals, CLI > MCP, & the end of localhost Daytona CEO Ivan Burazin explains why AI agents need composable computers, how Daytona pivoted from human dev environments to agent sandboxes, why bare metal and stateful snapshots matter, how RL workloads went from 0% to ~50% of usage, why Kubernetes breaks down at agent scale, and why the AI cloud may look more like Stripe than AWS.

🆕Daytona’s Agent-Native Compute: 60ms sandboxes, 50K startups in 75 sec, 850K daily runs, RL/evals, CLI > MCP, & the end of localhost Daytona CEO Ivan Burazin explains why AI agents need composable computers, how Daytona pivoted from human dev environments to agent sandboxes, why bare metal and stateful snapshots matter, how RL workloads went from 0% to ~50% of usage, why Kubernetes breaks down at agent scale, and why the AI cloud may look more like Stripe than AWS.

Latent.Space

12,972 views • 4 months ago

Have you tried Gemini Managed Agents? A single API call gives you a cloud sandbox where the Antigravity agent can research, code, and complete tasks. Can try it in the Google AI Studio playground or use our SDK to build agents into your own apps. Lots more on this soon! 😀

Have you tried Gemini Managed Agents? A single API call gives you a cloud sandbox where the Antigravity agent can research, code, and complete tasks. Can try it in the Google AI Studio playground or use our SDK to build agents into your own apps. Lots more on this soon! 😀

Jack Wotherspoon

11,692 views • 8 days ago

AI INTERVIEW: OPENAI'S SECRET WEAPON AI agents are no longer just hype—they're here to revolutionize automation, Web3, and beyond. SwarmNode.ai is building a serverless AI agent platform for scalability, efficiency, and real-world impact. In this exclusive interview, he reveals how AI swarms can outperform single models, why OpenAI’s Operator is just the beginning, and how crypto is fueling AI innovation. Plus, he breaks down DeepSeek’s game-changing AI breakthrough, the future of agent monetization, and why serverless AI could be the next frontier in automation. 01:37 – From Engineering to AI: The journey into artificial intelligence. 02:43 – The GPT-3 Moment: How OpenAI’s tech pulled him in. 04:10 – AI’s Biggest Challenge: Why real-world use cases lag behind. 05:05 – OpenAI’s Operator: Why it’s “rudimentary” (for now). 06:25 – Crypto & AI: How tokens help bootstrap AI startups. 08:15 – Can You Bootstrap a Startup with a Token? The trade-offs. 09:56 – 90% of AI Token Holders Don’t Use the Product—Does It Matter? 11:18 – What is SwarmNode?: AI agents, hosted serverlessly. 14:23 – AI Swarms: Why multiple agents outperform single models. 16:08 – What is a Swarm? A simple definition of collaborative AI. 17:32 – “How Can I Make Money with AI?”: Real-world use cases. 18:41 – AI Bounties: Hiring devs to build your custom agent. 20:50 – The Future of AI Marketplaces: Monetizing pre-built agents. 23:15 – DeepSeek’s Disruption: Why it’s good news for AI. 24:46 – Is SwarmNode Compatible with DeepSeek? How it integrates. 26:17 – SwarmNode vs. AI Launchpads: What makes it different? 27:42 – Why Serverless Matters: Cost savings & efficiency. 29:53 – AI Agents in the Real World: Booking flights, managing workflows, and more. 31:11 – Building SwarmNode for Developers: Why it started as a personal project. 32:27 – Explosive Growth: 200,000 AI agent executions in 5 weeks. 34:41 – Why SwarmNode Agents Aren’t Visible on 𝕏 Yet. 36:46 – Startup Hiring Lessons: Finding top AI talent. 39:15 – Why SwarmNode is Built in Python (and What’s Next). 40:32 – Scaling AI Workloads: Handling traffic surges. 41:42 – AWS & Cost Challenges: The biggest monetization hurdle. 42:58 – 2025: The Year of Mass AI Adoption. 45:22 – Should We Be Worried About AI’s Rapid Growth? 46:46 – The Most Underrated AI Tools Right Now. 47:34 – What’s Next for SwarmNode?: Making AI accessible to everyone.

AI INTERVIEW: OPENAI'S SECRET WEAPON AI agents are no longer just hype—they're here to revolutionize automation, Web3, and beyond. SwarmNode.ai is building a serverless AI agent platform for scalability, efficiency, and real-world impact. In this exclusive interview, he reveals how AI swarms can outperform single models, why OpenAI’s Operator is just the beginning, and how crypto is fueling AI innovation. Plus, he breaks down DeepSeek’s game-changing AI breakthrough, the future of agent monetization, and why serverless AI could be the next frontier in automation. 01:37 – From Engineering to AI: The journey into artificial intelligence. 02:43 – The GPT-3 Moment: How OpenAI’s tech pulled him in. 04:10 – AI’s Biggest Challenge: Why real-world use cases lag behind. 05:05 – OpenAI’s Operator: Why it’s “rudimentary” (for now). 06:25 – Crypto & AI: How tokens help bootstrap AI startups. 08:15 – Can You Bootstrap a Startup with a Token? The trade-offs. 09:56 – 90% of AI Token Holders Don’t Use the Product—Does It Matter? 11:18 – What is SwarmNode?: AI agents, hosted serverlessly. 14:23 – AI Swarms: Why multiple agents outperform single models. 16:08 – What is a Swarm? A simple definition of collaborative AI. 17:32 – “How Can I Make Money with AI?”: Real-world use cases. 18:41 – AI Bounties: Hiring devs to build your custom agent. 20:50 – The Future of AI Marketplaces: Monetizing pre-built agents. 23:15 – DeepSeek’s Disruption: Why it’s good news for AI. 24:46 – Is SwarmNode Compatible with DeepSeek? How it integrates. 26:17 – SwarmNode vs. AI Launchpads: What makes it different? 27:42 – Why Serverless Matters: Cost savings & efficiency. 29:53 – AI Agents in the Real World: Booking flights, managing workflows, and more. 31:11 – Building SwarmNode for Developers: Why it started as a personal project. 32:27 – Explosive Growth: 200,000 AI agent executions in 5 weeks. 34:41 – Why SwarmNode Agents Aren’t Visible on 𝕏 Yet. 36:46 – Startup Hiring Lessons: Finding top AI talent. 39:15 – Why SwarmNode is Built in Python (and What’s Next). 40:32 – Scaling AI Workloads: Handling traffic surges. 41:42 – AWS & Cost Challenges: The biggest monetization hurdle. 42:58 – 2025: The Year of Mass AI Adoption. 45:22 – Should We Be Worried About AI’s Rapid Growth? 46:46 – The Most Underrated AI Tools Right Now. 47:34 – What’s Next for SwarmNode?: Making AI accessible to everyone.

Mario Nawfal

338,311 views • 1 year ago

Agent development is moving forward. While production scaling traditionally required manual infrastructure setup and provisioning sandboxes from scratch, there's now a faster path. Managed Agents in the Gemini API are officially live. Get maximum agentic power with zero infrastructure overhead. One simple API call delivers a managed, remote sandbox for your agent so you can focus entirely on behavior. 📁 Fully customizable with your instructions, tools, and data via and 🌐 Test, iterate, and scale long-horizon tasks natively in the cloud. The hardest part of building agents is now the part you don't have to build. 👇 Get started now:

Agent development is moving forward. While production scaling traditionally required manual infrastructure setup and provisioning sandboxes from scratch, there's now a faster path. Managed Agents in the Gemini API are officially live. Get maximum agentic power with zero infrastructure overhead. One simple API call delivers a managed, remote sandbox for your agent so you can focus entirely on behavior. 📁 Fully customizable with your instructions, tools, and data via and 🌐 Test, iterate, and scale long-horizon tasks natively in the cloud. The hardest part of building agents is now the part you don't have to build. 👇 Get started now:

Google for Developers

39,294 views • 4 months ago

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

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 views • 4 months ago

Jev is a new model from the co-inventor of ChatGPT that can use computer tools in realtime right now it's playing Minecraft on its own computer in the cloud on Orgo this is what it looks like with just one Jev, but imagine: what about a thousand? or what about a billion of Jevs? each working together on their own computers in the cloud, discovering new science, running experiments, and designing new drugs 24/7. this is going to be bigger than ChatGPT

Jev is a new model from the co-inventor of ChatGPT that can use computer tools in realtime right now it's playing Minecraft on its own computer in the cloud on Orgo this is what it looks like with just one Jev, but imagine: what about a thousand? or what about a billion of Jevs? each working together on their own computers in the cloud, discovering new science, running experiments, and designing new drugs 24/7. this is going to be bigger than ChatGPT

Nick Vasilescu

16,613 views • 16 days ago

Jev and the System One Model: RLCD, intelligence/$, reliable AI, & the end of chat-first AI TypeSafe AI CEO Diogo Almeida explains why AI can solve extraordinarily hard problems yet still fail to automate basic work, why Jev is built for reliable decisions inside software instead of chat, why TypeSafe rejects public benchmarks and refusals at the API layer, why data and the right task matter more than brute-force compute, how System One Models could reshape coding agents and software, and why even with $1 billion he wouldn’t pre-train a model from scratch.

Jev and the System One Model: RLCD, intelligence/$, reliable AI, & the end of chat-first AI TypeSafe AI CEO Diogo Almeida explains why AI can solve extraordinarily hard problems yet still fail to automate basic work, why Jev is built for reliable decisions inside software instead of chat, why TypeSafe rejects public benchmarks and refusals at the API layer, why data and the right task matter more than brute-force compute, how System One Models could reshape coding agents and software, and why even with $1 billion he wouldn’t pre-train a model from scratch.

Latent.Space

411,057 views • 11 days ago

My talk from the AI Engineer Code Summit is out! 🚨 "How Claude Code Works" and what we can learn about frontier agent architectures. Coding agents are suddenly really really good, and I'm trying to understand why. In short: better models, simple loop design, and bash tools

My talk from the AI Engineer Code Summit is out! 🚨 "How Claude Code Works" and what we can learn about frontier agent architectures. Coding agents are suddenly really really good, and I'm trying to understand why. In short: better models, simple loop design, and bash tools

Jared Zoneraich

13,936 views • 9 months ago

Trillions in AI compute can't buy a $10 domain name. Jeff Weinstein explains how Stripe’s new machine payments protocol will unleash autonomous agents to control real budgets. (0:00) What Is Agentic Commerce? (2:00) What Is the Machine Payments Protocol? (4:11) Why Can’t Smart Agents Buy Things Online? (7:14) How Can You Safely Give an Agent a Budget? (9:34) How Can Agents Provision Cloud Services? (12:22) Why Does Machine Payments Need Stablecoins? (14:15) Why Did Stripe Co-Found the Tempo Blockchain? (16:52) Who Are the Early Adopters of Agent Payments? (18:38) Why Are Agents Now Stripe’s Primary Customer? (20:00) How Did Stripe Atlas Reach 100,000 Startups? (23:09) Why Are AI Startups Growing 50% Faster Now? (24:59) Who Is Smarter: Patrick or John Collison?

Trillions in AI compute can't buy a $10 domain name. Jeff Weinstein explains how Stripe’s new machine payments protocol will unleash autonomous agents to control real budgets. (0:00) What Is Agentic Commerce? (2:00) What Is the Machine Payments Protocol? (4:11) Why Can’t Smart Agents Buy Things Online? (7:14) How Can You Safely Give an Agent a Budget? (9:34) How Can Agents Provision Cloud Services? (12:22) Why Does Machine Payments Need Stablecoins? (14:15) Why Did Stripe Co-Found the Tempo Blockchain? (16:52) Who Are the Early Adopters of Agent Payments? (18:38) Why Are Agents Now Stripe’s Primary Customer? (20:00) How Did Stripe Atlas Reach 100,000 Startups? (23:09) Why Are AI Startups Growing 50% Faster Now? (24:59) Who Is Smarter: Patrick or John Collison?

Rex Salisbury

21,387 views • 3 months ago

From applied cryptography and offensive security in France’s defense industry to optimizing nuclear submarine workflows, then selling his e-signature startup to Docusign and now running AI as CTO of Superhuman Mail (Superhuman, recently acquired by Grammarly), Loïc Houssier has lived the full arc from deep infra and compliance hell to obsessing over 100ms product experiences and AI-native email. We sat down with Loïc to dig into how you actually put AI into an inbox without adding latency, why Superhuman leans so hard into agentic search and “Ask AI” over your entire email history, how they design tools vs. agents and fight agent laziness, what box-priced inference and local-first caching mean for cost and reliability, and his bet that your inbox will power your future AI EA while AI massively widens the gap between engineers with real fundamentals and those faking it. Ordinary Extrare Superhuman swyx Alessio Fanelli

From applied cryptography and offensive security in France’s defense industry to optimizing nuclear submarine workflows, then selling his e-signature startup to Docusign and now running AI as CTO of Superhuman Mail (Superhuman, recently acquired by Grammarly), Loïc Houssier has lived the full arc from deep infra and compliance hell to obsessing over 100ms product experiences and AI-native email. We sat down with Loïc to dig into how you actually put AI into an inbox without adding latency, why Superhuman leans so hard into agentic search and “Ask AI” over your entire email history, how they design tools vs. agents and fight agent laziness, what box-priced inference and local-first caching mean for cost and reliability, and his bet that your inbox will power your future AI EA while AI massively widens the gap between engineers with real fundamentals and those faking it. Ordinary Extrare Superhuman swyx Alessio Fanelli

Latent.Space

126,794 views • 9 months ago

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

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 views • 4 months ago