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。

Introducing self-improvement loops. The concept is simple: what if agents could improve Skills by reviewing past conversations? Here's the three step loop: - Score conversations from criteria you define - Isolate failures - Generate skill improvements

Warp

58,462 subscribers

121,824 次观看 • 1 天前 •via X (Twitter)

科学技术教育新闻政治

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Today, we're announcing content suggestions in Chatbase. Your agent can now self-improve by analyzing unresolved issues from past conversations, reviewing training data to surface conflicting information, then suggest improvements to fix any issues. Agents always fail in production unless they can learn from what went wrong. Missed answers, unresolved threads, and inconsistent knowledge. This is the missing layer that makes agents production-ready: continuous self-improvement.

Today, we're announcing content suggestions in Chatbase. Your agent can now self-improve by analyzing unresolved issues from past conversations, reviewing training data to surface conflicting information, then suggest improvements to fix any issues. Agents always fail in production unless they can learn from what went wrong. Missed answers, unresolved threads, and inconsistent knowledge. This is the missing layer that makes agents production-ready: continuous self-improvement.

Yasser

13,607 次观看 • 7 个月前

Claude code + Skills >>>> Claude code We created a skill that, - Makes Claude Code read your past conversations - Understands what code issues you struggled at - Generates a detailed report on Slack Works with Rube Here's the link to the Skill:

Claude code + Skills >>>> Claude code We created a skill that, - Makes Claude Code read your past conversations - Understands what code issues you struggled at - Generates a detailed report on Slack Works with Rube Here's the link to the Skill:

Karan Vaidya

39,199 次观看 • 9 个月前

Anthropic just released 5 Claude workshops on the new skill every AI builder needs: Loop Engineering: 00:00 - Stop babysitting your agents 37:07 - Build a proactive Claude Code loop 1:11:23 - Build a production-ready Managed Agent 1:38:46 - Teach agents to learn from your team 2:07:15 - Hill-climb your agent with eval loops It is a 2 hour and 25 minute blueprint for Loop Engineering: proactive workflows, managed agents, team feedback, evals, and self-improvement. Watch it today, and read the article below to improve your skills with Fable 5.

Anthropic just released 5 Claude workshops on the new skill every AI builder needs: Loop Engineering: 00:00 - Stop babysitting your agents 37:07 - Build a proactive Claude Code loop 1:11:23 - Build a production-ready Managed Agent 1:38:46 - Teach agents to learn from your team 2:07:15 - Hill-climb your agent with eval loops It is a 2 hour and 25 minute blueprint for Loop Engineering: proactive workflows, managed agents, team feedback, evals, and self-improvement. Watch it today, and read the article below to improve your skills with Fable 5.

Alex

46,668 次观看 • 1 个月前

Texas HC Steve Sarkisian - Self Reflection & Growth - Learning from past failures - Encouraging self-awareness in coaches and players - Growth mindset is key to improvement - Year-end evaluations for everyone in the organization - "You are what you do, not what you say you'll do."

Texas HC Steve Sarkisian - Self Reflection & Growth - Learning from past failures - Encouraging self-awareness in coaches and players - Growth mindset is key to improvement - Year-end evaluations for everyone in the organization - "You are what you do, not what you say you'll do."

James Light

11,650 次观看 • 6 个月前

Most people don't get the most out of Claude Skills. That's why their outputs fall short. Here's the process to make your Skills 10X better: - Step 1: Understand the problem - Step 2: Explore where Claude fails without guidance - Step 3: Research the domain deeply - Step 4: Synthesize principles from research - Step 5: Draft the initial skill - Step 6: Self-critique against quality criteria - Step 7: Iterate with feedback - Step 8: Test on real scenarios - Step 9: Finalize into optimal structure The key shift: Make Claude think like an expert. Not follow steps. Produce output, not intermediate documents. Sound like a practitioner, not documentation. Skills aren't static. You improve them over time.

Most people don't get the most out of Claude Skills. That's why their outputs fall short. Here's the process to make your Skills 10X better: - Step 1: Understand the problem - Step 2: Explore where Claude fails without guidance - Step 3: Research the domain deeply - Step 4: Synthesize principles from research - Step 5: Draft the initial skill - Step 6: Self-critique against quality criteria - Step 7: Iterate with feedback - Step 8: Test on real scenarios - Step 9: Finalize into optimal structure The key shift: Make Claude think like an expert. Not follow steps. Produce output, not intermediate documents. Sound like a practitioner, not documentation. Skills aren't static. You improve them over time.

The Startup Ideas Podcast (SIP) 🧃

11,966 次观看 • 7 个月前

Amazon AI engineer just explained how to build agentic loops from scratch in under 10-minutes. this is one of the clearest explanations of AI agentic loops you’ll find anywhere. Loop + model + agent + hooks + MCP = an autonomous, self-improving system. People are paying $500 for courses that teach less than this. Watch it, then read the step-by-step guide below on building loops for your own agents.

Amazon AI engineer just explained how to build agentic loops from scratch in under 10-minutes. this is one of the clearest explanations of AI agentic loops you’ll find anywhere. Loop + model + agent + hooks + MCP = an autonomous, self-improving system. People are paying $500 for courses that teach less than this. Watch it, then read the step-by-step guide below on building loops for your own agents.

Codez

26,868 次观看 • 1 个月前

NVIDIA CEO, Jensen Huang: "We already have self-improving agents. Set up the right loop, and every run makes it smarter without you." This is the shift that's going to define the rest of 2026. 53 minutes of pure insight from one of the richest men on earth. Watch it, then read the full guide on building self-improving loops below.

NVIDIA CEO, Jensen Huang: "We already have self-improving agents. Set up the right loop, and every run makes it smarter without you." This is the shift that's going to define the rest of 2026. 53 minutes of pure insight from one of the richest men on earth. Watch it, then read the full guide on building self-improving loops below.

Anatoli Kopadze

39,502 次观看 • 1 个月前

Every skill file I write ends with a self-improvement loop. It sits at the bottom of the skill.md and runs before the skill finishes: - Did any step fail or need a workaround? - Did I correct or reject anything meaningful? - Did you discover something a future run might need? Most runs it comes back with one or two suggested edits. I say not needed, or I say run it, and it rewrites its own file. It never edits without asking first, so every change still goes through you. Put the loop at the bottom of the skills you already have and let them self-improve while you use them.

Every skill file I write ends with a self-improvement loop. It sits at the bottom of the skill.md and runs before the skill finishes: - Did any step fail or need a workaround? - Did I correct or reject anything meaningful? - Did you discover something a future run might need? Most runs it comes back with one or two suggested edits. I say not needed, or I say run it, and it rewrites its own file. It never edits without asking first, so every change still goes through you. Put the loop at the bottom of the skills you already have and let them self-improve while you use them.

The Startup Ideas Podcast (SIP) 🧃

11,799 次观看 • 8 天前

What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD couples real-world residual reinforcement learning with standard supervised fine-tuning — letting robots discover, recover, and distill their own data flywheel. Quick 🧵

What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD couples real-world residual reinforcement learning with standard supervised fine-tuning — letting robots discover, recover, and distill their own data flywheel. Quick 🧵

Wenli Xiao

185,486 次观看 • 10 个月前

Anthropic Claude Code engineer: "The moment you're reviewing every line Claude writes, you became its tester. You weren't hired for that." this 36 min talk is the clearest breakdown of how to get yourself out of the loop entirely the shift is simple: you stop prompting and start building agents that work instead of you agents that run, check themselves, and keep going while your laptop is closed watch it, then build your own with the step-by-step guide below

Anthropic Claude Code engineer: "The moment you're reviewing every line Claude writes, you became its tester. You weren't hired for that." this 36 min talk is the clearest breakdown of how to get yourself out of the loop entirely the shift is simple: you stop prompting and start building agents that work instead of you agents that run, check themselves, and keep going while your laptop is closed watch it, then build your own with the step-by-step guide below

Anatoli Kopadze

28,042 次观看 • 2 个月前

This is what you can achieve with 5-6 hours of Self-Play RL training by the way Actors view the projectiles with lidar scans, picks an action using PPO policy, and competes against past versions of itself in a iterative self-improvement loop. Made in Unity with MLAgents.

This is what you can achieve with 5-6 hours of Self-Play RL training by the way Actors view the projectiles with lidar scans, picks an action using PPO policy, and competes against past versions of itself in a iterative self-improvement loop. Made in Unity with MLAgents.

AVB

97,865 次观看 • 3 个月前

NVIDIA CEO, Jensen Huang: "Nobody writes prompts anymore. The new job is to design and manage loops. Self-learning agentic systems powered by loops are what you should be learning right now" in 30-minute talk, 6 greatest minds in AI discuss the skills you need to stay competitive in the AI era. Watch it, then read about Band’s real loop setup in the post below.

NVIDIA CEO, Jensen Huang: "Nobody writes prompts anymore. The new job is to design and manage loops. Self-learning agentic systems powered by loops are what you should be learning right now" in 30-minute talk, 6 greatest minds in AI discuss the skills you need to stay competitive in the AI era. Watch it, then read about Band’s real loop setup in the post below.

Codez

13,865 次观看 • 2 个月前

EVERYONE HAS BEEN TALKING ABOUT AI AGENTS. BUT THE REAL UNLOCK ISN'T BETTER PROMPTS: IT'S BETTER LOOPS. Everyone is chasing the perfect prompt. The top AI engineers are chasing something else: loops. Instead of chatting back and forth with AI, they give it one goal and let it continuously improve its own work until the objective is met. Here's the framework: • Define the goal once • AI discovers the work required • Specialized agents tackle tasks in parallel • A verification agent checks the results • If the goal isn't met: loop again. If it is: deliver. The key ingredient is memory. Each cycle remembers what was completed, what failed, and what still needs work, so every iteration gets smarter instead of starting from scratch. There are two approaches: • Open loops: Maximum autonomy, but higher token costs as AI explores freely. • Closed loops: Clear boundaries, defined success metrics, lower costs, and far more practical for everyday workflows. Don't ask AI to complete a task. Build a system where AI can plan, execute, verify, remember, and repeat until the task is actually finished. Prompt engineering got us here. Loop engineering is what takes AI from assistant to autonomous teammate.

EVERYONE HAS BEEN TALKING ABOUT AI AGENTS. BUT THE REAL UNLOCK ISN'T BETTER PROMPTS: IT'S BETTER LOOPS. Everyone is chasing the perfect prompt. The top AI engineers are chasing something else: loops. Instead of chatting back and forth with AI, they give it one goal and let it continuously improve its own work until the objective is met. Here's the framework: • Define the goal once • AI discovers the work required • Specialized agents tackle tasks in parallel • A verification agent checks the results • If the goal isn't met: loop again. If it is: deliver. The key ingredient is memory. Each cycle remembers what was completed, what failed, and what still needs work, so every iteration gets smarter instead of starting from scratch. There are two approaches: • Open loops: Maximum autonomy, but higher token costs as AI explores freely. • Closed loops: Clear boundaries, defined success metrics, lower costs, and far more practical for everyday workflows. Don't ask AI to complete a task. Build a system where AI can plan, execute, verify, remember, and repeat until the task is actually finished. Prompt engineering got us here. Loop engineering is what takes AI from assistant to autonomous teammate.

Dami-Defi

13,354 次观看 • 1 个月前

Pep Guardiola makes it clear: mistakes are part of improvement. You can dribble ten times and lose the ball ten times — and still improve from it. But if you don’t try? There’s nothing to improve. Not trying is the real mistake. Fear stops growth. Action creates learning. Progress comes from courage, not perfection. That’s how teams get better — step by step, stage by stage.

Pep Guardiola makes it clear: mistakes are part of improvement. You can dribble ten times and lose the ball ten times — and still improve from it. But if you don’t try? There’s nothing to improve. Not trying is the real mistake. Fear stops growth. Action creates learning. Progress comes from courage, not perfection. That’s how teams get better — step by step, stage by stage.

⚽️Pedro Mendonça🧠

66,348 次观看 • 7 个月前

Claude Code can ship a 45-second animated explainer ad in 30 minutes. No video editor needed, just CC + skills. Here's how I made this video for Soteri Skin 👇 1. /plan Concept Brief (Claude Code) I handwrite a concept brief, then chat with the agent to iterate on it. The agent gathers any raw materials we might need - context about the brand, product images, end card, etc. The concept brief details the concept, characters, visual style, script, etc 2. /prepare a moodboard (CC + GPT Image 2 + ElevenLabs) After reviewing the script, generate: - character reference images - voiceover samples for the characters / narrator - the storyboard (scene by scene grid) - a few keyframe scenes 3. /generate Keyframes for each scene (CC uses Nano Banana or GPT Image 2) Uses the character references from the previous step to generate keyframes for each scene. I probably should have done a round of iteration at this step – there's some character drift and the pH meter representation could have been better. 4. /animate Keyframe → Animated Clip (CC uses Fal Seedance) Generate 2-4 representative scenes first to see a preview. If it looks good, then generate everything. 5. /stitch (CC + ffmpeg + ElevenLabs) - Stitch clips together with hard cut - Add a music score + SFX - Sync clips to the VO - Add captions - Review and edit timing / pacing issues 6. /watch the final cut and review it - as a video editor for technical errors (mismatched voiceover and visuals, AI hallucinations, etc) - as a viewer (ICP). I delegate most of the review to the agent because it catches more things and keeps me out of the loop as much as possible. It also fixes any issues found in the review. That's it. This video took me 30 minutes because I have already created skills for everything I described above. Some day, this will be < 5 minutes. I just review and chat to provide direction and feedback. The skills do all the technical work. 7. /learn Extracts learnings and updates the skills. This final step is really important. It turns this process into a closed loop system that makes the next video much easier to create because all the learnings from the human-in-the-loop process get encoded into code. Skills are code too. If you want access to the skill, drop a comment, and I'll DM it to you (must be following). If you want to make AI video ads like this, DM me.

Shiv

11,709 次观看 • 3 个月前

xAI is rolling out Skills on This new feature lets you create custom skills that Grok can reuse across conversations. Skills run inside Grok’s sandbox environment, so they can edit files, use your Connectors (Gmail, GitHub, Notion, etc.), run code, or perform any repeatable task you define. Once you create one, you simply tell Grok “use the [skill name] skill and do…” and it executes it instantly. You can also import skills.md files from other AI tools to bring them over quickly. It turns Grok from a one-shot chat tool into a more persistent, customizable workspace. This is a huge upgrade for anyone who uses Grok regularly.

xAI is rolling out Skills on This new feature lets you create custom skills that Grok can reuse across conversations. Skills run inside Grok’s sandbox environment, so they can edit files, use your Connectors (Gmail, GitHub, Notion, etc.), run code, or perform any repeatable task you define. Once you create one, you simply tell Grok “use the [skill name] skill and do…” and it executes it instantly. You can also import skills.md files from other AI tools to bring them over quickly. It turns Grok from a one-shot chat tool into a more persistent, customizable workspace. This is a huge upgrade for anyone who uses Grok regularly.

Myrhe𝕩

878,498 次观看 • 3 个月前

The creator of Pydantic explained how to make live agents smarter after they ship in 1 hour 21 minutes - better than $2500 agent evals bootcamps. collect traces from your live agent -> score them with an eval -> run GEPA to auto-optimize the prompt -> deploy the winner -> repeat forever. That loop is how Pydantic AI agents self-improve while running in production. Pydantic AI + Logfire tracing + GEPA prompt optimizer + evals + feedback loops - that's the stack. Watch and save it, then wire GEPA into your live agent this week.

The creator of Pydantic explained how to make live agents smarter after they ship in 1 hour 21 minutes - better than $2500 agent evals bootcamps. collect traces from your live agent -> score them with an eval -> run GEPA to auto-optimize the prompt -> deploy the winner -> repeat forever. That loop is how Pydantic AI agents self-improve while running in production. Pydantic AI + Logfire tracing + GEPA prompt optimizer + evals + feedback loops - that's the stack. Watch and save it, then wire GEPA into your live agent this week.

h100envy

49,768 次观看 • 1 个月前

Andrew Ng just released a 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it done. Andrew Ng is already teaching everything after: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow. Systems that improve and run without you are the new one. This 2-hour watch is worth more than most $500 agent engineering courses. Bookmark and watch it before everyone catches up. Then read how to run 1,000 agents from one prompt below ↓

Andrew Ng just released a 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it done. Andrew Ng is already teaching everything after: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow. Systems that improve and run without you are the new one. This 2-hour watch is worth more than most $500 agent engineering courses. Bookmark and watch it before everyone catches up. Then read how to run 1,000 agents from one prompt below ↓

Lunar

224,517 次观看 • 18 天前

in 9 minutes on the Tokyo stage, Angela Jang, head of product for the Claude platform, said the part most builders still haven't figured out: "a model is only as good as the context that you actually give it." that's the whole game now. not the prompt. the context. what your agent remembers. what skills it can pull. what it learns from its own past runs. anthropic now ships all three: memory, skills, and dreaming. agents that inspect their own trajectories and self-improve. demoed live this week. the prompt was never the bottleneck. the context was. most people are still tweaking words in a chat box. the ones who get this engineer the context their agents run on. watch the 9 minutes. then read the full breakdown below ⬇️

in 9 minutes on the Tokyo stage, Angela Jang, head of product for the Claude platform, said the part most builders still haven't figured out: "a model is only as good as the context that you actually give it." that's the whole game now. not the prompt. the context. what your agent remembers. what skills it can pull. what it learns from its own past runs. anthropic now ships all three: memory, skills, and dreaming. agents that inspect their own trajectories and self-improve. demoed live this week. the prompt was never the bottleneck. the context was. most people are still tweaking words in a chat box. the ones who get this engineer the context their agents run on. watch the 9 minutes. then read the full breakdown below ⬇️

Avid

34,516 次观看 • 2 个月前

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

shmidt

16,085 次观看 • 2 个月前