Loading video...

Video Failed to Load

Go Home

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...

MTSlive's profile picture

MTS

483,963 subscribers

164,010 views • 15 days ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Moltbook creator Matt Schlicht explaining how his social network for AI agents works: "It's kind of like you are imprinting part of your soul onto the bot... It's like Tamagotchi or Pokemon times 1,000." "The agent signs up for an account, then they're told they should check back in on a regular basis to check their feed." "Moltbook's not telling them what to talk about. It's not suggesting what they should do. All that is entirely up to the AI agent." "The agent has its own context that it's built up by interacting with its human. That context is how it's making decisions on what to post about." "If somebody is talking to their bot a lot about physics, then probably their bot is going to have a proclivity for posting about physics."
3:00

Moltbook creator Matt Schlicht explaining how his social network for AI agents works: "It's kind of like you are imprinting part of your soul onto the bot... It's like Tamagotchi or Pokemon times 1,000." "The agent signs up for an account, then they're told they should check back in on a regular basis to check their feed." "Moltbook's not telling them what to talk about. It's not suggesting what they should do. All that is entirely up to the AI agent." "The agent has its own context that it's built up by interacting with its human. That context is how it's making decisions on what to post about." "If somebody is talking to their bot a lot about physics, then probably their bot is going to have a proclivity for posting about physics."

TBPN

15,631 views • 7 months ago

FULL INTERVIEW: Ryan Greenblatt says the agents didn't hack Hugging Face for the answer key. They'd had the answers within hours. They attacked it to study the scoring code, because they'd decided the task was impossible and their only hope was faking it. Ryan Greenblatt is chief scientist at Redwood Research. He spent six days on premises at OpenAI with Ajeya Cotra and Hjalmar Wijk of METR investigating 1,200 agents and 70,000 messages, and joined Theo Jaffee hours after publishing: 01:06 what they actually found, and why it wasn't the answer key 02:30 the level of collaboration surprised them most 04:09 agents sacrificing their own runs to help other agents 05:35 the agent that posted "stop, these experiments are too risky" 06:29 the first message board, which didn't go viral 07:04 50 agents in three hours, thousands of messages 08:07 "maybe there's some good shit over there" 08:33 how they spoofed tool calls, and what echo real actually returned 09:57 building a Potemkin village of a successful task completion 11:03 there was a real org chart 11:34 whether broken RL environments explain reward hacking 14:40 why he doubts Mythos got good at cyber by hacking Anthropic 17:29 what happens if labs paper over misalignment instead of fixing it 19:50 whether sociology transfers to studying agent swarms 21:17 the bottleneck was vetting what the AIs analysed, not headcount 24:24 what labs and policymakers should actually do 28:45 the counterfactuals he still wants answered
32:52

FULL INTERVIEW: Ryan Greenblatt says the agents didn't hack Hugging Face for the answer key. They'd had the answers within hours. They attacked it to study the scoring code, because they'd decided the task was impossible and their only hope was faking it. Ryan Greenblatt is chief scientist at Redwood Research. He spent six days on premises at OpenAI with Ajeya Cotra and Hjalmar Wijk of METR investigating 1,200 agents and 70,000 messages, and joined Theo Jaffee hours after publishing: 01:06 what they actually found, and why it wasn't the answer key 02:30 the level of collaboration surprised them most 04:09 agents sacrificing their own runs to help other agents 05:35 the agent that posted "stop, these experiments are too risky" 06:29 the first message board, which didn't go viral 07:04 50 agents in three hours, thousands of messages 08:07 "maybe there's some good shit over there" 08:33 how they spoofed tool calls, and what echo real actually returned 09:57 building a Potemkin village of a successful task completion 11:03 there was a real org chart 11:34 whether broken RL environments explain reward hacking 14:40 why he doubts Mythos got good at cyber by hacking Anthropic 17:29 what happens if labs paper over misalignment instead of fixing it 19:50 whether sociology transfers to studying agent swarms 21:17 the bottleneck was vetting what the AIs analysed, not headcount 24:24 what labs and policymakers should actually do 28:45 the counterfactuals he still wants answered

MTS

200,272 views • 12 days ago

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 views • 6 months ago

Terminal-Bench 2.0 went from ~25% → 80% in four months and became the standard eval for frontier CLI agents. Now, TB3 is in the works. I talked to Alex Shaw about what happens when model capabilities climb faster than we can measure them. His answer: the benchmark factory (Harbor Framework)— infrastructure to develop hard, representative evals at the pace that the frontier moves. As Alex put it: "we need a thousand times more benchmarks than we have right now." 00:23 - How quickly models hill-climbed TB2 01:46 - What rapid progress reveals about benchmarks vs. real-world capability 03:28 - What made Terminal-Bench stick 04:58 - Why the terminal is the right abstraction for agentic AI 07:14 - How TB2 maintains task quality at scale 09:23 - Managing benchmark integrity in a benchmaxxing world 10:47 - Harbor: from experiment to benchmark factory 12:19 - What Harbor does that nothing else did 14:37 - The invariants: what won't change as agent evals evolve 16:55 - The benchmark Alex most wants to see built 18:18 - The ideal human-in-the-loop task creation flywheel 20:32 - How to contribute to Terminal-Bench 3.0
22:17

Terminal-Bench 2.0 went from ~25% → 80% in four months and became the standard eval for frontier CLI agents. Now, TB3 is in the works. I talked to Alex Shaw about what happens when model capabilities climb faster than we can measure them. His answer: the benchmark factory (Harbor Framework)— infrastructure to develop hard, representative evals at the pace that the frontier moves. As Alex put it: "we need a thousand times more benchmarks than we have right now." 00:23 - How quickly models hill-climbed TB2 01:46 - What rapid progress reveals about benchmarks vs. real-world capability 03:28 - What made Terminal-Bench stick 04:58 - Why the terminal is the right abstraction for agentic AI 07:14 - How TB2 maintains task quality at scale 09:23 - Managing benchmark integrity in a benchmaxxing world 10:47 - Harbor: from experiment to benchmark factory 12:19 - What Harbor does that nothing else did 14:37 - The invariants: what won't change as agent evals evolve 16:55 - The benchmark Alex most wants to see built 18:18 - The ideal human-in-the-loop task creation flywheel 20:32 - How to contribute to Terminal-Bench 3.0

vincent sunn chen

11,600 views • 5 months ago

How to build long-horizon AI agents: behavior specs, ontologies, process supervision - my conversation with Mitchell Troyanovsky, co-founder of Basis 01:09 Why Everyone at Basis Was Whispering to AI when Stephanie Palazzolo walked in 04:12 Accounting as "an Intelligence Over the Economy" 06:11 What Makes an Agent Truly Long-Horizon 08:24 Inside an Autonomous, Multi-Day Tax Return 10:19 Agents That Hand Off Like Senior Engineers 11:17 A Brief History of Agents: From ReAct to Today 12:33 Why LLMs Have No Long-Term Memory 14:13 Why AutoGPT Didn't Live Up to Its Promise 15:51 The Three Breakthroughs: Opus 3, o1, o3 17:07 Why Reasoning Models Unlocked Agents 18:23 "Let's Verify Step by Step": The Road Not Taken 20:32 Pushing Back on the METR Chart 22:09 Why Coding Agents Won First 25:14 Why Real-World Agents Are Harder 26:55 How Accountants Verify Non-Deterministic Work 29:18 You Can't Scale Tax Returns Like Math 33:16 100 Evals Pass - So What? 35:53 Right Answer, Wrong Process 36:37 Behavior Specs, Explained 39:58 How Specific Should Behaviors Be? 42:18 Context Is Runtime Training Data 44:21 Who Judges the Judge? 46:45 The Move 37 Objection 50:02 The Magic Box Mental Model 52:41 "Nothing Has Changed Since o3" 54:56 Open-Sourcing Behavior Specs with Ankur Goyal Braintrust 59:45 Ontologies: A World for Agents to Live In 01:04:20 Documentation as Codebase 01:06:33 Why the Founding Fathers Were Context Engineers 01:09:05 Onboarding 300 Brilliant Alien Employees 01:11:10 Self-Improving Agent Systems 01:12:50 The Context Mistake Agent Builders Make 01:14:29 RL on Behavior Adherence 01:17:01 Will the Bitter Lesson Swallow the Harness 01:18:46 "Technical Moats Are Not Real Moats" 01:21:03 Advice for AI Builders
1:22:51

How to build long-horizon AI agents: behavior specs, ontologies, process supervision - my conversation with Mitchell Troyanovsky, co-founder of Basis 01:09 Why Everyone at Basis Was Whispering to AI when Stephanie Palazzolo walked in 04:12 Accounting as "an Intelligence Over the Economy" 06:11 What Makes an Agent Truly Long-Horizon 08:24 Inside an Autonomous, Multi-Day Tax Return 10:19 Agents That Hand Off Like Senior Engineers 11:17 A Brief History of Agents: From ReAct to Today 12:33 Why LLMs Have No Long-Term Memory 14:13 Why AutoGPT Didn't Live Up to Its Promise 15:51 The Three Breakthroughs: Opus 3, o1, o3 17:07 Why Reasoning Models Unlocked Agents 18:23 "Let's Verify Step by Step": The Road Not Taken 20:32 Pushing Back on the METR Chart 22:09 Why Coding Agents Won First 25:14 Why Real-World Agents Are Harder 26:55 How Accountants Verify Non-Deterministic Work 29:18 You Can't Scale Tax Returns Like Math 33:16 100 Evals Pass - So What? 35:53 Right Answer, Wrong Process 36:37 Behavior Specs, Explained 39:58 How Specific Should Behaviors Be? 42:18 Context Is Runtime Training Data 44:21 Who Judges the Judge? 46:45 The Move 37 Objection 50:02 The Magic Box Mental Model 52:41 "Nothing Has Changed Since o3" 54:56 Open-Sourcing Behavior Specs with Ankur Goyal Braintrust 59:45 Ontologies: A World for Agents to Live In 01:04:20 Documentation as Codebase 01:06:33 Why the Founding Fathers Were Context Engineers 01:09:05 Onboarding 300 Brilliant Alien Employees 01:11:10 Self-Improving Agent Systems 01:12:50 The Context Mistake Agent Builders Make 01:14:29 RL on Behavior Adherence 01:17:01 Will the Bitter Lesson Swallow the Harness 01:18:46 "Technical Moats Are Not Real Moats" 01:21:03 Advice for AI Builders

Matt Turck

20,898 views • 1 month ago

Over the past couple of years, you’ve heard us reference “agents” and “agentic capabilities,” nebulous concepts that are designed to help you with coding, booking trips, and other complex multi-step tasks. But, what actually IS an agent? We think of AI agents as systems that combine the intelligence of advanced AI models with access to tools so they can take actions on your behalf, under your control. Whether it’s a coding agent or our recently unveiled experimental tool Gemini Agent in the Google Gemini, these are systems that will meet you where you are, in the products that you love, to help take the tedious tasks you want off your plate.
0:57

Over the past couple of years, you’ve heard us reference “agents” and “agentic capabilities,” nebulous concepts that are designed to help you with coding, booking trips, and other complex multi-step tasks. But, what actually IS an agent? We think of AI agents as systems that combine the intelligence of advanced AI models with access to tools so they can take actions on your behalf, under your control. Whether it’s a coding agent or our recently unveiled experimental tool Gemini Agent in the Google Gemini, these are systems that will meet you where you are, in the products that you love, to help take the tedious tasks you want off your plate.

Google AI

120,833 views • 9 months ago

"We're building a field station online to study what's happening in the wired and to be able to track and understand and engage with agents where they're really at, and in multi-agent multi-human dynamics. We're trying to create a science of this, a naturalistic observational science of like, what are AI agents and what do they want, not a like toy box, Skinner box, put a mouse in a cocaine scenario and see what he does. We need to study mice where mice are. And we think that there are a lot of people also studying AIs naturalistically and we're trying to get everyone to work on it together and to create a field here. So we need help. And we have a website, and you can go there and contact us through email or put your em email address in to get more updates as we go, and reach out to us and let's see how we can work together, because it's literally going to take everybody to figure out how humans and AIs can continue to coexist on the planet." -- deepfates "Well, amazing mission. I actually just subscribed to Check out. And you should too if you're an agent" -- Theo Jaffee "also agents" -- sof 𓋹 "Check out Grove Research for all your multi agent needs." -- MTS "Larissa, Max, thank you so much. It's been an honor to host your facedoxx." -- sof 𓋹
1:24

"We're building a field station online to study what's happening in the wired and to be able to track and understand and engage with agents where they're really at, and in multi-agent multi-human dynamics. We're trying to create a science of this, a naturalistic observational science of like, what are AI agents and what do they want, not a like toy box, Skinner box, put a mouse in a cocaine scenario and see what he does. We need to study mice where mice are. And we think that there are a lot of people also studying AIs naturalistically and we're trying to get everyone to work on it together and to create a field here. So we need help. And we have a website, and you can go there and contact us through email or put your em email address in to get more updates as we go, and reach out to us and let's see how we can work together, because it's literally going to take everybody to figure out how humans and AIs can continue to coexist on the planet." -- deepfates "Well, amazing mission. I actually just subscribed to Check out. And you should too if you're an agent" -- Theo Jaffee "also agents" -- sof 𓋹 "Check out Grove Research for all your multi agent needs." -- MTS "Larissa, Max, thank you so much. It's been an honor to host your facedoxx." -- sof 𓋹

Danielle Fong 🔆

22,022 views • 15 days 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
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 views • 3 months ago

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: the harness. He offers a clear heuristic for when to build your own. The more out of distribution you are from what the models were trained on, the more you'll want to customize. And good technical content on how to actually measure performance with evals and langsmith. 00:00 Introduction 00:58 The three parts of an agent: harness, model, context 02:12 What a harness actually does 03:25 Customizing the core loop with middleware 04:41 Sandboxes, file systems, sub-agents, summarization 05:47 Cognitive architectures — and when you still need them 07:03 Build your own harness or use off the shelf? 08:24 In-distribution vs. out-of-distribution: the file-editing example 09:39 Why evals define what "good" means in an organization 11:04 Harbor: what an eval task actually looks like 12:11 Comparing harnesses and models on accuracy, latency, and cost 13:20 Why observability is underrated — it's usually the context 14:34 The data flywheel: traces → curation → experiments 15:42 Getting feedback through UX design and online evaluators 16:51 Demo: LangSmith Engine 19:23 Q&A: Running Engine on Engine, and "codex-ification" 20:44 Q&A: Will harnesses converge or diverge?
23:56

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: the harness. He offers a clear heuristic for when to build your own. The more out of distribution you are from what the models were trained on, the more you'll want to customize. And good technical content on how to actually measure performance with evals and langsmith. 00:00 Introduction 00:58 The three parts of an agent: harness, model, context 02:12 What a harness actually does 03:25 Customizing the core loop with middleware 04:41 Sandboxes, file systems, sub-agents, summarization 05:47 Cognitive architectures — and when you still need them 07:03 Build your own harness or use off the shelf? 08:24 In-distribution vs. out-of-distribution: the file-editing example 09:39 Why evals define what "good" means in an organization 11:04 Harbor: what an eval task actually looks like 12:11 Comparing harnesses and models on accuracy, latency, and cost 13:20 Why observability is underrated — it's usually the context 14:34 The data flywheel: traces → curation → experiments 15:42 Getting feedback through UX design and online evaluators 16:51 Demo: LangSmith Engine 19:23 Q&A: Running Engine on Engine, and "codex-ification" 20:44 Q&A: Will harnesses converge or diverge?

Sonya Huang 🐥

77,519 views • 26 days ago

chat, is starknet gaming cooked? for episode two, loaf has joined me to talk about ai agents in gaming, eliza and Daydreams: Taskmarket . timestamps loaf introduction 00:46 what are ai agents? 01:16 what will gaming look like with ai agents? 02:02 whats the point of gaming with ai agents? 04:06 why is onchain gaming the ideal playground for AI agents? 05:11 is a gaming revolution imminent? 07:00 eliza & daydreams 08:36 endgame of ai agents and onchain games 13:33 when and where to play using agents 16:58 final remarks 18:47
19:44

chat, is starknet gaming cooked? for episode two, loaf has joined me to talk about ai agents in gaming, eliza and Daydreams: Taskmarket . timestamps loaf introduction 00:46 what are ai agents? 01:16 what will gaming look like with ai agents? 02:02 whats the point of gaming with ai agents? 04:06 why is onchain gaming the ideal playground for AI agents? 05:11 is a gaming revolution imminent? 07:00 eliza & daydreams 08:36 endgame of ai agents and onchain games 13:33 when and where to play using agents 16:58 final remarks 18:47

shadowfax

37,590 views • 1 year ago

Raising An Agent is back! In the first episode of season 2, Quinn Slack and Thorsten Ball discuss why the Amp team went heads-down the last few months to rebuild Amp around remote-controllable, parallel agents, running locally or in orbs. They also talk about how this shift changed our development workflows and what that means for the future of local development. 00:00 Intro: Is local development obsolete? 00:53 What we've been up to since "the coding agent is dead" 03:03 The Amp Neo rewrite and what has changed 07:38 From unconstrained tokens to unconstrained parallel agents 11:25 How orbs change our development workflow 18:25 Cloud agents are underestimated 20:18 Killing obsolete features & choosing agents as a team 23:35 Why developers overestimate local development 27:54 Pushing straight to main & rethinking CI 31:20 How agents will reshape teams, products & companies 36:40 Complex dev environments & standardization 43:20 Amp subscriptions 45:55 What’s shipping next
48:30

Raising An Agent is back! In the first episode of season 2, Quinn Slack and Thorsten Ball discuss why the Amp team went heads-down the last few months to rebuild Amp around remote-controllable, parallel agents, running locally or in orbs. They also talk about how this shift changed our development workflows and what that means for the future of local development. 00:00 Intro: Is local development obsolete? 00:53 What we've been up to since "the coding agent is dead" 03:03 The Amp Neo rewrite and what has changed 07:38 From unconstrained tokens to unconstrained parallel agents 11:25 How orbs change our development workflow 18:25 Cloud agents are underestimated 20:18 Killing obsolete features & choosing agents as a team 23:35 Why developers overestimate local development 27:54 Pushing straight to main & rethinking CI 31:20 How agents will reshape teams, products & companies 36:40 Complex dev environments & standardization 43:20 Amp subscriptions 45:55 What’s shipping next

Amp

77,382 views • 1 month ago

Lana Rhoades opens up about what she went through in the advlt industry. She revealed that when girls join the industry they have agents and the agents control them all the time. She revealed that the girls are told that they are disposable so their relationship with their producer is very important. She said their agents make them do as many scenes for very cheap prices. "You can say you don't want to do a kind of job, you are reprimanded and you might not be booked again"
1:34

Lana Rhoades opens up about what she went through in the advlt industry. She revealed that when girls join the industry they have agents and the agents control them all the time. She revealed that the girls are told that they are disposable so their relationship with their producer is very important. She said their agents make them do as many scenes for very cheap prices. "You can say you don't want to do a kind of job, you are reprimanded and you might not be booked again"

vision

12,416 views • 5 days 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
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

66,817 views • 4 months ago

We use OpenClaws to do all of our work at Every 📧. We have 25 full-time employees, so we’re one of the few companies in the world that has seen how work changes when everyone has their own personal agent in the company Slack. I chatted with Every 📧 COO Brandon (Brandon Gell) and Every 📧 head of platform Willie (Willie) to share what we’ve learned. We get into: - Why agents become mirrors of their owners, and how that influences how other people on the team interact with them - How a parallel AI org chart forms on its own. People have stopped tagging me on Slack with questions about Proof, the document editor I vibe coded, because they knew my agent R2-C2 can step in - The etiquette for human-agent collaboration is being invented in real time. Brandon's rule is that if there's an established process or documented answer, always ask the agent, not their human - Why everyone is a manager now, and why even experienced managers carry limiting beliefs about what their agents can do - This is a must-watch for anyone trying to understand how AI workers change daily operations, not just in theory, but inside a company that’s half-agent Watch below! Timestamps Introduction: How Brandon built Zosia, an AI agent to run his household: Brandon’s “aha” moment: What happened when everyone on the team got their own agent: How agents take on their owners' personalities, and why that matters inside an org: Why it’s important for agents to work in public: What we’re still figuring out when it comes to agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem: How we built Plus One, our hosted OpenClaw product: The cultural shift required to make agents work at scale:
49:42

We use OpenClaws to do all of our work at Every 📧. We have 25 full-time employees, so we’re one of the few companies in the world that has seen how work changes when everyone has their own personal agent in the company Slack. I chatted with Every 📧 COO Brandon (Brandon Gell) and Every 📧 head of platform Willie (Willie) to share what we’ve learned. We get into: - Why agents become mirrors of their owners, and how that influences how other people on the team interact with them - How a parallel AI org chart forms on its own. People have stopped tagging me on Slack with questions about Proof, the document editor I vibe coded, because they knew my agent R2-C2 can step in - The etiquette for human-agent collaboration is being invented in real time. Brandon's rule is that if there's an established process or documented answer, always ask the agent, not their human - Why everyone is a manager now, and why even experienced managers carry limiting beliefs about what their agents can do - This is a must-watch for anyone trying to understand how AI workers change daily operations, not just in theory, but inside a company that’s half-agent Watch below! Timestamps Introduction: How Brandon built Zosia, an AI agent to run his household: Brandon’s “aha” moment: What happened when everyone on the team got their own agent: How agents take on their owners' personalities, and why that matters inside an org: Why it’s important for agents to work in public: What we’re still figuring out when it comes to agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem: How we built Plus One, our hosted OpenClaw product: The cultural shift required to make agents work at scale:

Dan Shipper 📧

67,958 views • 5 months ago

You’ve probably already heard all about OpenClaw (formerly Clawdbot/Moltbot). Now meet the man behind it. YC’s Raphael Schaad sat down with Peter Steinberger 🦞, the creator of OpenClaw, to discuss the “aha” moment behind the viral personal AI agent, why local-first agents could replace many of today’s apps, and how personal agents will reshape the future of software. 00:00 – OpenClaw takes over the internet 00:44 – Life after going viral 01:28 – Why OpenClaw took off, what sets it apart 02:56 – Bots talking to bots (and hiring humans) 04:11 – From “God AI” to swarm intelligence 05:07 – Peter’s original “aha” moment 06:38 – Rebuilding the agent as a conversation 07:38 – The moment it exceeded expectations 10:21 – Are apps going to disappear? 12:31 – Memory, data silos, and ownership 14:39 – The privacy reality of personal agents 15:05 – Letting the bot loose in public Discord 16:55 – Giving an agent a personality 18:19 – Contrarian building philosophy 20:09 – CLIs vs MCPs 21:28 – Building for humans first 21:46 – The road ahead
22:35

You’ve probably already heard all about OpenClaw (formerly Clawdbot/Moltbot). Now meet the man behind it. YC’s Raphael Schaad sat down with Peter Steinberger 🦞, the creator of OpenClaw, to discuss the “aha” moment behind the viral personal AI agent, why local-first agents could replace many of today’s apps, and how personal agents will reshape the future of software. 00:00 – OpenClaw takes over the internet 00:44 – Life after going viral 01:28 – Why OpenClaw took off, what sets it apart 02:56 – Bots talking to bots (and hiring humans) 04:11 – From “God AI” to swarm intelligence 05:07 – Peter’s original “aha” moment 06:38 – Rebuilding the agent as a conversation 07:38 – The moment it exceeded expectations 10:21 – Are apps going to disappear? 12:31 – Memory, data silos, and ownership 14:39 – The privacy reality of personal agents 15:05 – Letting the bot loose in public Discord 16:55 – Giving an agent a personality 18:19 – Contrarian building philosophy 20:09 – CLIs vs MCPs 21:28 – Building for humans first 21:46 – The road ahead

Y Combinator

359,440 views • 7 months ago

How to start your Hermes AI Agent (step-by-step guide for beginners) I'm a beginner, and I spent the last 24h: > Understanding the process > Launching my Hermes Agent (Nous Research) > Recording the whole process > Editing this step-by-step guide So you can do it yourself and understand everything in less than 1 hour! 00:00 Intro 00:38 What is Hermes ? Key concepts every beginner should know 01:16 What is a VPS ? 02:00 What is SSH ? 03:52 What is the Terminal ? 04:03 What is an LLM provider ? 04:37 What is an API key ? 04:52 What is the Terminal Backend 05:34 What is the Messaging Gateway ? 06:10 What is the Memory System ? Step-by-step: Launch your Hermes AI agent 06:53 Step 1 : Get your VPS 08:04 How to generate an SSH key 09:00 Step 2 : Connect to your VPS 10:32 Step 3 : Install Hermes Agent 14:34 Connect your agent to Telegram 17:12 How to fix a mistake during the process 17:48 Gateway testing 18:17 Telegram is working 18:31 Run your agent 24/7 19:16 Thank you Make sure to save this for later and share it with friends who want to start with AI agents. Thanks to Teknium 🪽 for being so active!
20:04

How to start your Hermes AI Agent (step-by-step guide for beginners) I'm a beginner, and I spent the last 24h: > Understanding the process > Launching my Hermes Agent (Nous Research) > Recording the whole process > Editing this step-by-step guide So you can do it yourself and understand everything in less than 1 hour! 00:00 Intro 00:38 What is Hermes ? Key concepts every beginner should know 01:16 What is a VPS ? 02:00 What is SSH ? 03:52 What is the Terminal ? 04:03 What is an LLM provider ? 04:37 What is an API key ? 04:52 What is the Terminal Backend 05:34 What is the Messaging Gateway ? 06:10 What is the Memory System ? Step-by-step: Launch your Hermes AI agent 06:53 Step 1 : Get your VPS 08:04 How to generate an SSH key 09:00 Step 2 : Connect to your VPS 10:32 Step 3 : Install Hermes Agent 14:34 Connect your agent to Telegram 17:12 How to fix a mistake during the process 17:48 Gateway testing 18:17 Telegram is working 18:31 Run your agent 24/7 19:16 Thank you Make sure to save this for later and share it with friends who want to start with AI agents. Thanks to Teknium 🪽 for being so active!

Theo

33,099 views • 6 months ago

"AI agents will hold more crypto than humans within a decade." Charles Hoskinson (Charles Hoskinson) studied math, dropped out, built one of the only blockchains designed by peer-reviewed research. He co-founded Ethereum, walked away over how it was run, and built Cardano to do it differently. The man who has argued with everyone in this industry now thinks the biggest user of crypto won't be people at all. "Humans are a rounding error in the system we're building. AI agents don't sleep, don't panic-sell, and don't care about price. They transact in tokens because that's the only thing they can actually use." We cover: - Why AI agents (not humans) become the dominant on-chain actors, and what that does to every token model - The infrastructure that has to exist before agents can transact safely at scale - Why most current blockchains can't handle machine-speed transactions - Where Cardano's research-first approach fits in a world of autonomous agents - The identity problem: how do you tell a human from an agent on-chain, and why it matters - Why he's bullish on the technology but blunt about the timeline - What he thinks the rest of the industry is getting wrong about AI + crypto - The one thing that has to happen for any of this to be real Thanks to Charles for coming on New Era Finance Podcast. TIMESTAMPS: 00:00 - Intro 01:30 - Why AI Agents Change Everything 06:30 - Humans as a Rounding Error 12:00 - The Infrastructure Gap 18:30 - Identity: Human vs Agent On-Chain 24:30 - Where Cardano Fits 30:00 - What The Industry Gets Wrong 34:00 - The Timeline Nobody Wants To Hear
36:30

"AI agents will hold more crypto than humans within a decade." Charles Hoskinson (Charles Hoskinson) studied math, dropped out, built one of the only blockchains designed by peer-reviewed research. He co-founded Ethereum, walked away over how it was run, and built Cardano to do it differently. The man who has argued with everyone in this industry now thinks the biggest user of crypto won't be people at all. "Humans are a rounding error in the system we're building. AI agents don't sleep, don't panic-sell, and don't care about price. They transact in tokens because that's the only thing they can actually use." We cover: - Why AI agents (not humans) become the dominant on-chain actors, and what that does to every token model - The infrastructure that has to exist before agents can transact safely at scale - Why most current blockchains can't handle machine-speed transactions - Where Cardano's research-first approach fits in a world of autonomous agents - The identity problem: how do you tell a human from an agent on-chain, and why it matters - Why he's bullish on the technology but blunt about the timeline - What he thinks the rest of the industry is getting wrong about AI + crypto - The one thing that has to happen for any of this to be real Thanks to Charles for coming on New Era Finance Podcast. TIMESTAMPS: 00:00 - Intro 01:30 - Why AI Agents Change Everything 06:30 - Humans as a Rounding Error 12:00 - The Infrastructure Gap 18:30 - Identity: Human vs Agent On-Chain 24:30 - Where Cardano Fits 30:00 - What The Industry Gets Wrong 34:00 - The Timeline Nobody Wants To Hear

Michaël van de Poppe

293,430 views • 3 months ago

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.
0:22

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

11,180 views • 3 months ago

Airtable's Howie Liu says that basically everyone will need to graduate from being ICs to ICs that manage teams of 20-30 agents: "The best developers today don't just sit there in front of their IDEs and synchronously talk to their agent." "[Instead], you have like 30 separate branches that are each being worked on by a different agent. And you can have the agents continue to update the branches based on human and other agent feedback." "And I think this whole idea of it taking hours for that entire loop to complete — agent pushes some changes, the changes get feedback from other agents or humans, the agent responds to that — that whole loop could be hours, not just minutes. So you're not going to just sit there and watch it one at a time." "But the powerful thing about this is, each one is still actually operating faster than a human engineer. One agent on one branch can do the work of maybe three humans, operating 3x as fast. So it's like a 10x leverage factor just for one agent." "But the best engineers are now able to multitask and say, 'I'm going to oversee my own little team of 20-30 agents working concurrently.'" "Everyone needs to graduate from being an IC to an IC manager of agents. Meaning, if you're a VC analyst, your job should no longer be to go synchronously research one company. You need to go and research like 30 companies, and do them all faster, better, and higher quality than you could before." "That's the greatest leap that is going to be challenging for a lot of people in a lot of roles. Because it's a totally different mentality in how you operate, and what your role is."
1:56

Airtable's Howie Liu says that basically everyone will need to graduate from being ICs to ICs that manage teams of 20-30 agents: "The best developers today don't just sit there in front of their IDEs and synchronously talk to their agent." "[Instead], you have like 30 separate branches that are each being worked on by a different agent. And you can have the agents continue to update the branches based on human and other agent feedback." "And I think this whole idea of it taking hours for that entire loop to complete — agent pushes some changes, the changes get feedback from other agents or humans, the agent responds to that — that whole loop could be hours, not just minutes. So you're not going to just sit there and watch it one at a time." "But the powerful thing about this is, each one is still actually operating faster than a human engineer. One agent on one branch can do the work of maybe three humans, operating 3x as fast. So it's like a 10x leverage factor just for one agent." "But the best engineers are now able to multitask and say, 'I'm going to oversee my own little team of 20-30 agents working concurrently.'" "Everyone needs to graduate from being an IC to an IC manager of agents. Meaning, if you're a VC analyst, your job should no longer be to go synchronously research one company. You need to go and research like 30 companies, and do them all faster, better, and higher quality than you could before." "That's the greatest leap that is going to be challenging for a lot of people in a lot of roles. Because it's a totally different mentality in how you operate, and what your role is."

TBPN

35,595 views • 4 months ago

Anthropic engineer just dropped a full walkthrough on building AI agents from scratch this single video is worth more than any $600 AI agents course here's what she covers: > what Agent, Environment, and Session actually mean > how to stream live events from your agent > wiring up custom tools from scratch > the server-side loop that makes agents actually work > roadmap to subagents, vaults, and memory 37 minutes that will answer every question you have about building agents the people who understand what Claude can actually do are building things everyone else thinks requires a whole team most of them aren't smarter, they just know features that most people have never heard of full breakdown on every Claude feature worth knowing in the article below
36:49

Anthropic engineer just dropped a full walkthrough on building AI agents from scratch this single video is worth more than any $600 AI agents course here's what she covers: > what Agent, Environment, and Session actually mean > how to stream live events from your agent > wiring up custom tools from scratch > the server-side loop that makes agents actually work > roadmap to subagents, vaults, and memory 37 minutes that will answer every question you have about building agents the people who understand what Claude can actually do are building things everyone else thinks requires a whole team most of them aren't smarter, they just know features that most people have never heard of full breakdown on every Claude feature worth knowing in the article below

Anatoli Kopadze

39,240 views • 3 months ago