正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

ANTHROPIC JUST INTRODUCED A FEATURE THAT LETS CLAUDE REVIEW AND IMPROVE ITS OWN WORK OVER TIME. The new “Dreaming” workflow helps agents learn from mistakes, refine outputs in the background, and improve task completion without changing the model itself.

0xMarioNawfal

263,004 subscribers

53,484 次观看 • 4 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 条评论

Mykola Kondratiuk 的头像

Mykola Kondratiuk4 个月前

calling it self-improvement skips the hard part. the fleet you reviewed Friday isn't the fleet running Monday

Asif Usman 的头像

Asif Usman4 个月前

Self-improving agents change the game completely.

Gregor 的头像

Gregor4 个月前

What counts as "learning" if the model itself doesn't change? Sounds like it's just storing corrected outputs and routing through them.

Coffee fans 的头像

Coffee fans4 个月前

Background loops save tokens, but self-feedback drifts fast without strict evals.

BraveTom 的头像

BraveTom4 个月前

Cool 😎

I Pun Daddy 的头像

I Pun Daddy4 个月前

Claude reviewing its own work? Guess someone's figured out how to automate the internal QA process.

Scriba 的头像

Scriba4 个月前

this is closer to what matters than most people realize. the model doesn't need to get smarter. the workflow around it needs to get smarter. we've been building self-correcting loops into our agents for months. the difference in output quality is night and day.

TrueStandard 的头像

TrueStandard4 个月前

anthropic noted that the ai gets details wrong about real people, events, or places. refining outputs in the background helps, but the model still struggles to attribute quotes to the correct person. precision remains the primary obstacle for autonomous workflows.

Sanarsh 的头像

Sanarsh4 个月前

Claude's now sleeping on its failures till it ghosts them.

相关视频

In just 12 minutes, the Head of Claude walks through how Fable 5 enables agents that learn, adapt, and improve over time.

In just 12 minutes, the Head of Claude walks through how Fable 5 enables agents that learn, adapt, and improve over time.

0xMarioNawfal

55,491 次观看 • 3 个月前

Anthropic engineer: "Over 90% of Anthropic engineers use a self-improving agentic loop for coding. The key is to close the loop: give the agent a way to verify and improve its own work" In this 12-minute talk, an Anthropic engineer explains how to build an agent that continuously improves itself. Claude + routines + loops + CLAUDE.md - that's the foundation. Skip Netflix tonight. Save this post!

Anthropic engineer: "Over 90% of Anthropic engineers use a self-improving agentic loop for coding. The key is to close the loop: give the agent a way to verify and improve its own work" In this 12-minute talk, an Anthropic engineer explains how to build an agent that continuously improves itself. Claude + routines + loops + CLAUDE.md - that's the foundation. Skip Netflix tonight. Save this post!

unicode

62,153 次观看 • 2 个月前

Anthropic engineer: "The fastest way to make an agent better isn't a smarter model, it's the right loop and graph around it." In 60 minutes she breaks down how Anthropic engineers use Claude Code, build agents that catch their own mistakes and improve with every run. This beats any $500 agentic engineering course you can find. Watch it, then read the full guide on loops and graphs below.

Anthropic engineer: "The fastest way to make an agent better isn't a smarter model, it's the right loop and graph around it." In 60 minutes she breaks down how Anthropic engineers use Claude Code, build agents that catch their own mistakes and improve with every run. This beats any $500 agentic engineering course you can find. Watch it, then read the full guide on loops and graphs below.

Anatoli Kopadze

135,539 次观看 • 1 个月前

Introducing Claude agents in Notion. Your task board is Claude’s to-do list. Anthropic runs the model and the agent harness. Notion is the orchestration layer: context, UI, and a shared place for teams to review and ship, and kick off Claude workflows. Join the waitlist:

Introducing Claude agents in Notion. Your task board is Claude’s to-do list. Anthropic runs the model and the agent harness. Notion is the orchestration layer: context, UI, and a shared place for teams to review and ship, and kick off Claude workflows. Join the waitlist:

Notion

495,433 次观看 • 5 个月前

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents" "Close the loop, give the model a way to verify its own output" In a 20-minute session, an Anthropic Team member breaks down how to build agents that improve themselves The real setup is Claude running through loops, plan mode, and dynamic workflows Better than most $300 agent courses Bookmark and watch the talk Then read the article below

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents" "Close the loop, give the model a way to verify its own output" In a 20-minute session, an Anthropic Team member breaks down how to build agents that improve themselves The real setup is Claude running through loops, plan mode, and dynamic workflows Better than most $300 agent courses Bookmark and watch the talk Then read the article below

rari

382,629 次观看 • 3 个月前

𝜃 ZeroEval helps you build reliable AI agents through evaluations that learn from their mistakes and get better over time. Congrats on the launch, seb and xtamales!

𝜃 ZeroEval helps you build reliable AI agents through evaluations that learn from their mistakes and get better over time. Congrats on the launch, seb and xtamales!

Y Combinator

23,867 次观看 • 1 年前

$ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK. It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass. How to run it: 1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart. 2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done. 3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents. Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens. Bookmark this.$

ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK. It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass. How to run it: 1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart. 2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done. 3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents. Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens. Bookmark this.

Yarchi

462,450 次观看 • 3 个月前

anthropic research lead: “99% of our engineers use 300+ AI agents working together.” “close the loop. let the AI check its own work.” in a 20-minute talk, an Anthropic team member explains how to build AI agents that can improve themselves. the setup uses Claude with loops, plan mode, and smart workflows. it’s better than most $300 AI agent courses. bookmark this and watch the talk. then read the article below.

anthropic research lead: “99% of our engineers use 300+ AI agents working together.” “close the loop. let the AI check its own work.” in a 20-minute talk, an Anthropic team member explains how to build AI agents that can improve themselves. the setup uses Claude with loops, plan mode, and smart workflows. it’s better than most $300 AI agent courses. bookmark this and watch the talk. then read the article below.

MIKE

34,813 次观看 • 2 个月前

Anthropic engineer: "I went from babysitting agents to setting one goal and leaving. The right workflow does the rest." In 23 minutes he breaks down his exact workflow that makes agents run for days without him, learn from their mistakes, and get smarter with every run. Worth more than any paid course on building with agents. Watch the session, then read the guide on building loops below.

Anthropic engineer: "I went from babysitting agents to setting one goal and leaving. The right workflow does the rest." In 23 minutes he breaks down his exact workflow that makes agents run for days without him, learn from their mistakes, and get smarter with every run. Worth more than any paid course on building with agents. Watch the session, then read the guide on building loops below.

Anatoli Kopadze

56,246 次观看 • 2 个月前

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." In 45 minutes she breaks down how Anthropic builds agents that remember, learn from their mistakes, and get smarter with every run. Worth more than any paid course you'll find on building agents. Watch the session, then read the guide on building loops below.

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." In 45 minutes she breaks down how Anthropic builds agents that remember, learn from their mistakes, and get smarter with every run. Worth more than any paid course you'll find on building agents. Watch the session, then read the guide on building loops below.

Anatoli Kopadze

3,174,858 次观看 • 2 个月前

ANTHROPIC 🔥: Claude Tag is coming to Claude Desktop in the form of collaborative Projects for Claude Code. That's essentially a built-in Slack 👀 > Earlier spotted Managed Projects feature got a slight upgrade, mentioning that users will be able to spawn different threads within a single project session. > Project creation UI got a new option to add repositories as context, which will be used across all sessions. The upcoming Projects for Claude Code feature is expected to enable teams and individuals to work collaboratively inside Claude Desktop, as they would with Claude Tag on Slack. Claude Code Projects will have persistent context and memory, which Claude will periodically refine and improve over time.

ANTHROPIC 🔥: Claude Tag is coming to Claude Desktop in the form of collaborative Projects for Claude Code. That's essentially a built-in Slack 👀 > Earlier spotted Managed Projects feature got a slight upgrade, mentioning that users will be able to spawn different threads within a single project session. > Project creation UI got a new option to add repositories as context, which will be used across all sessions. The upcoming Projects for Claude Code feature is expected to enable teams and individuals to work collaboratively inside Claude Desktop, as they would with Claude Tag on Slack. Claude Code Projects will have persistent context and memory, which Claude will periodically refine and improve over time.

🚨 AI News | TestingCatalog

90,939 次观看 • 1 个月前

ExACT combines Reflective-MCTS and Exploratory Learning to improve AI agents' decision-making, enabling test-time compute scaling. Learn how these methods help agents refine strategies for state-of-the-art performance and improved computational efficiency:

ExACT combines Reflective-MCTS and Exploratory Learning to improve AI agents' decision-making, enabling test-time compute scaling. Learn how these methods help agents refine strategies for state-of-the-art performance and improved computational efficiency:

Microsoft Research

13,274 次观看 • 1 年前

Neurode recently introduced the world's first drug-free ADHD treatment headset. It helps improve focus, impulse control, and memory in just 20 minutes a day. Neurode tracks brain activity in real time, offering an “MRI in your pocket” that lets you monitor progress and take control of your ADHD symptoms.

Neurode recently introduced the world's first drug-free ADHD treatment headset. It helps improve focus, impulse control, and memory in just 20 minutes a day. Neurode tracks brain activity in real time, offering an “MRI in your pocket” that lets you monitor progress and take control of your ADHD symptoms.

Ritwik Pavan

70,762 次观看 • 2 年前

Anthropic engineer: "You're not supposed to watch Claude Code work. You're supposed to wake up and review what it shipped" in 22 minutes she builds the full workflow from scratch, step by step a routine that ships work while you sleep most developers have never seen Claude Code run without them watching watch the session, then save the guide below

Anthropic engineer: "You're not supposed to watch Claude Code work. You're supposed to wake up and review what it shipped" in 22 minutes she builds the full workflow from scratch, step by step a routine that ships work while you sleep most developers have never seen Claude Code run without them watching watch the session, then save the guide below

Anatoli Kopadze

36,289 次观看 • 3 个月前

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." In 45 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run. This beats any paid course on agents I've seen. Watch it, then read the guide on building loops below.

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." In 45 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run. This beats any paid course on agents I've seen. Watch it, then read the guide on building loops below.

Anatoli Kopadze

305,296 次观看 • 23 天前

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." In 45 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run. This beats any paid course on agents I've seen. Watch it, then read the guide on building loops below.

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." In 45 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run. This beats any paid course on agents I've seen. Watch it, then read the guide on building loops below.

Anatoli Kopadze

2,144,011 次观看 • 2 个月前

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." In 45 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run. This beats any paid course on agents I've seen. Watch it, then read the guide on building loops below.

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." In 45 minutes she shows exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run. This beats any paid course on agents I've seen. Watch it, then read the guide on building loops below.

Anatoli Kopadze

205,622 次观看 • 13 天前

Robots are getting smarter, but most still fail the same way. They don’t learn from their own mistakes. A new paper proposes something different: a way for robots to self-improve directly from their failures in the real world. It’s called PLD (Probe, Learn, Distill). The idea: instead of collecting endless human demos, let the robot figure out where it fails, learn how to recover, and then distill that knowledge back into its main model. Key takeaways from the research: ✅ Uses residual reinforcement learning to recover from policy failures ✅ Achieves 99% success on LIBERO and 100% on real Franka and YAM arms ✅ Runs hour-long manipulation tasks without human resets ✅ Builds a feedback loop between real-world data and model adaptation Unlike supervised fine-tuning, which relies on humans, PLD learns from the robot’s own experience. By training on its own failure distribution, the model becomes both more efficient and more aligned with the real world. It’s not just a technical shift, it’s a step toward robots that improve themselves through real-world practice. Thanks for sharing, Wenli Xiao !! Paper and demos: —- Weekly robotics and AI insights. Subscribe free:

Robots are getting smarter, but most still fail the same way. They don’t learn from their own mistakes. A new paper proposes something different: a way for robots to self-improve directly from their failures in the real world. It’s called PLD (Probe, Learn, Distill). The idea: instead of collecting endless human demos, let the robot figure out where it fails, learn how to recover, and then distill that knowledge back into its main model. Key takeaways from the research: ✅ Uses residual reinforcement learning to recover from policy failures ✅ Achieves 99% success on LIBERO and 100% on real Franka and YAM arms ✅ Runs hour-long manipulation tasks without human resets ✅ Builds a feedback loop between real-world data and model adaptation Unlike supervised fine-tuning, which relies on humans, PLD learns from the robot’s own experience. By training on its own failure distribution, the model becomes both more efficient and more aligned with the real world. It’s not just a technical shift, it’s a step toward robots that improve themselves through real-world practice. Thanks for sharing, Wenli Xiao !! Paper and demos: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

22,881 次观看 • 10 个月前

Anthropic research lead: "99% of our engineers are running swarms of 300+ self-improving agents. close the agent loop. Give the model a way to verify its own output" in a 20-minute session, Anthropic team member explains how to build a model that improves itself. Claude + loops + plan mode + dynamic workflows -that’s the secret. Watch the talk, then save the playbook below.

Anthropic research lead: "99% of our engineers are running swarms of 300+ self-improving agents. close the agent loop. Give the model a way to verify its own output" in a 20-minute session, Anthropic team member explains how to build a model that improves itself. Claude + loops + plan mode + dynamic workflows -that’s the secret. Watch the talk, then save the playbook below.

Codez

668,847 次观看 • 3 个月前

Generate photorealistic textures from text prompts with the new Text to Texture feature, now available in #Substance3DSampler (beta). Improve your workflow by spending less time hunting for reference imagery, and more time bringing your creative vision to life.

Generate photorealistic textures from text prompts with the new Text to Texture feature, now available in #Substance3DSampler (beta). Improve your workflow by spending less time hunting for reference imagery, and more time bringing your creative vision to life.

Adobe Substance 3D

484,254 次观看 • 2 年前