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。

Andrej Karpathy: "Vibe coding is amazing. But Agentic + Opus 5.5 harness engineering is the next level. 99% of my coding routine is automated by AI agents." In this 30-minute talk, Andrej Karpathy explains how to build an AI agent workflow from scratch. Worth more than any $500 agentic... show more

Hanako

23,071 subscribers

36,753 次观看 • 4 天前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

13 条评论

slash1s 的头像

slash1s4 天前

huh I didn’t see it

Nathan | Product Designer 的头像

Nathan | Product Designer4 天前

If 99% of the coding is automated, the last 1% is reading what the agents did and asking "why" 😅

Fede 的头像

Fede4 天前

@bot let’s review this, remind me of watching it

Bông 的头像

Bông3 天前

Nội dung này đánh giá cao kỹ thuật AI và đề xuất xem bài nói chuyện của Karpathy.

Sofie g. 的头像

Sofie g.3 天前

Claiming 99% automation overlooks the deep architectural understanding required for novel problems. Where does the agent's capability end and the human's essential design input begin?

Vipul Kumar Kewat 的头像

Vipul Kumar Kewat3 天前

The mix of music and visuals here is perfect.

Emly 的头像

Emly3 天前

Exciting to see AI's advanced capabilities in automation.

The SI Maximalist 的头像

The SI Maximalist3 天前

There’s something wonderfully nerdy about automating the coding routine and finding a whole new engineering project in the harness

Dusan 🐧 AI agents · dad 的头像

Dusan 🐧 AI agents · dad4 天前

what does he still keep in the 1% he does by hand?

Hrundel75 🐷 的头像

Hrundel75 🐷4 天前

Always guy with ru name

catman 的头像

catman3 天前

Pick one repetitive task and automate it end to end before trying to automate your whole coding routine. Keep a human approval step until you’ve measured how often the agent’s output passes your tests without edits.

安叫兽|Bird🕊️ 🔶 BNB 的头像

安叫兽|Bird🕊️ 🔶 BNB3 天前

30分钟就能讲清的东西，很多课偏要拆成好几章。

Hailu 🍏 的头像

Hailu 🍏3 天前

Bài viết này nhấn mạnh sự đột phá của tác nhân AI trong mã hóa.

相关视频

Andrej Karpathy: “Vibe coding is incredible. But Agentic + Opus 5.5 harness engineering is the next level. 99% of my coding routine is automated by AI agents.” In this 30-minute talk, Andrej Karpathy explains how to build an AI agent workflow from scratch. Worth more than $500 agentic engineering course on the internet. Watch it today, then read the full guide for Opus 5.5 Harness Engineering

Andrej Karpathy: “Vibe coding is incredible. But Agentic + Opus 5.5 harness engineering is the next level. 99% of my coding routine is automated by AI agents.” In this 30-minute talk, Andrej Karpathy explains how to build an AI agent workflow from scratch. Worth more than $500 agentic engineering course on the internet. Watch it today, then read the full guide for Opus 5.5 Harness Engineering

hayato

61,446 次观看 • 17 天前

Andrej Karpathy: "Vibe coding is amazing. But Agentic + Opus 5.5 harness engineering is the next level. 99% of my coding routine is automated by AI agents." In this 30-minute talk, Andrej Karpathy breaks down how to build an AI agent workflow from scratch. Worth more than any $500 agentic engineering course on the internet. Watch it today, then read the article below ↓

Andrej Karpathy: "Vibe coding is amazing. But Agentic + Opus 5.5 harness engineering is the next level. 99% of my coding routine is automated by AI agents." In this 30-minute talk, Andrej Karpathy breaks down how to build an AI agent workflow from scratch. Worth more than any $500 agentic engineering course on the internet. Watch it today, then read the article below ↓

Kyrox

26,287 次观看 • 7 天前

Andrej Karpathy: "The future is not writing code. The future is writing the loops that write the code. The leverage point has moved one floor up." This is the shift that defines the next era of coding and quant building. 1 hour of pure insight on agentic AI coding and loop engineering from the OpenAI co-founder who just joined Anthropic to build self improving Claude. Worth more than every $500 vibe coding course combined. Watch it, then read the full guide on how to build your first self improving quant trading loop below.

Andrej Karpathy: "The future is not writing code. The future is writing the loops that write the code. The leverage point has moved one floor up." This is the shift that defines the next era of coding and quant building. 1 hour of pure insight on agentic AI coding and loop engineering from the OpenAI co-founder who just joined Anthropic to build self improving Claude. Worth more than every $500 vibe coding course combined. Watch it, then read the full guide on how to build your first self improving quant trading loop below.

Roan

38,246 次观看 • 4 个月前

Claude Code creator: “100% of my code has been written by Claude since Opus 4.5. most of my coding routine is automated by loops & dynamic workflows" In this 40-minute video, Boris shares how to build a self-improving agentic setup from scratch. Loops + dynamic workflows + auto mode + routines - that’s the secret. Worth more than a $500 vibe-coding course. Watch today, then read below to learn how to build the same workflow.

Claude Code creator: “100% of my code has been written by Claude since Opus 4.5. most of my coding routine is automated by loops & dynamic workflows" In this 40-minute video, Boris shares how to build a self-improving agentic setup from scratch. Loops + dynamic workflows + auto mode + routines - that’s the secret. Worth more than a $500 vibe-coding course. Watch today, then read below to learn how to build the same workflow.

Codez

119,418 次观看 • 4 个月前

Andrej Karpathy (Andrej Karpathy), OpenAI co-founder, ex-Tesla AI, "vibe coding" creator. In just 4 mins, he explains why Claude Skills, MCP servers, and AI agents are past the hype and are now the new baseline for building. Worth every second ↓

Andrej Karpathy (Andrej Karpathy), OpenAI co-founder, ex-Tesla AI, "vibe coding" creator. In just 4 mins, he explains why Claude Skills, MCP servers, and AI agents are past the hype and are now the new baseline for building. Worth every second ↓

Charly Wargnier ♨️

418,758 次观看 • 7 个月前

Andrej Karpathy (Andrej Karpathy) — co-founded OpenAI, led AI at Tesla, coined "vibe coding." In 4 minutes he explains why software is changing - and why Claude Skills, MCP servers, and AI agents aren't hype anymore. They're the foundation of how software gets built from now on. Imo, worth every second (i've added subtitles)👇

Andrej Karpathy (Andrej Karpathy) — co-founded OpenAI, led AI at Tesla, coined "vibe coding." In 4 minutes he explains why software is changing - and why Claude Skills, MCP servers, and AI agents aren't hype anymore. They're the foundation of how software gets built from now on. Imo, worth every second (i've added subtitles)👇

darkzodchi

454,887 次观看 • 7 个月前

Creator of Claude Code: “I’m not just prompting agents anymore. I’m building a harness with graphs and loops - and the agents inside it are building my agent. In 3–6 months, we’ll all be engineering harnesses for our agentic systems.” In this 10-minute talk, Boris Cherny reveals what the future of agentic engineering will look like. Worth more than a $500 agentic AI course. Watch it today, then read the complete guide to building an agent harness in the article below.

Creator of Claude Code: “I’m not just prompting agents anymore. I’m building a harness with graphs and loops - and the agents inside it are building my agent. In 3–6 months, we’ll all be engineering harnesses for our agentic systems.” In this 10-minute talk, Boris Cherny reveals what the future of agentic engineering will look like. Worth more than a $500 agentic AI course. Watch it today, then read the complete guide to building an agent harness in the article below.

Ichigo

74,378 次观看 • 1 个月前

Andrew Ng: “Agents are the most important trend in AI right now - 100% of my tasks already done by agents. in 3-6 months, we’ll all be building Graphs to orchestrate self-improving agents. No more prompting.” in a 20-minute talk, Andrew Ng explains how to build self-improving agentic systems from scratch. Worth more than a $500 agentic course. Watch this talk, then read how to become an agent orchestrator with graph engineering below.

Andrew Ng: “Agents are the most important trend in AI right now - 100% of my tasks already done by agents. in 3-6 months, we’ll all be building Graphs to orchestrate self-improving agents. No more prompting.” in a 20-minute talk, Andrew Ng explains how to build self-improving agentic systems from scratch. Worth more than a $500 agentic course. Watch this talk, then read how to become an agent orchestrator with graph engineering below.

Movez

35,824 次观看 • 3 个月前

SpaceXAI engineer (ex-Cursor): "at SpaceXAI, 85% of our code is already written by GrokBot agents. I'm not coding - I'm building GrokBot teams who do this for me i'm running 10-20 GrokBot agents in a loop. I have a Chief of Staff agent, he is managing all coding agents" in a 20-minute workshop, SpaceXAI engineers reveal how they build AI agents internally worth more than a $500 agentic engineering course watch today, then read how to build a team of GrokBot agents from scratch in the article below

SpaceXAI engineer (ex-Cursor): "at SpaceXAI, 85% of our code is already written by GrokBot agents. I'm not coding - I'm building GrokBot teams who do this for me i'm running 10-20 GrokBot agents in a loop. I have a Chief of Staff agent, he is managing all coding agents" in a 20-minute workshop, SpaceXAI engineers reveal how they build AI agents internally worth more than a $500 agentic engineering course watch today, then read how to build a team of GrokBot agents from scratch in the article below

Movez

117,736 次观看 • 1 个月前

Google Brain founder, Andrew Ng: “In future, 100% of tasks will be done by AI agents. 80% of my tasks are already done by Claude & GrokBot agents. Prompting is gone.” in 25-minute talk, he explains how the future of AI Engineering will look like - and how to prepare for it. worth more than a $500 AI engineering course. watch it today, then read the full breakdown on building agentic teams with GrokBot in the article below.

Google Brain founder, Andrew Ng: “In future, 100% of tasks will be done by AI agents. 80% of my tasks are already done by Claude & GrokBot agents. Prompting is gone.” in 25-minute talk, he explains how the future of AI Engineering will look like - and how to prepare for it. worth more than a $500 AI engineering course. watch it today, then read the full breakdown on building agentic teams with GrokBot in the article below.

Movez

10,356 次观看 • 17 天前

Anthropic engineers just showed how to build agentic systems that run for days using "loops." "At Anthropic, >30% of our code is already written by loops - that's how we ship so fast. in this 40-minute workshop, they reveal the whole stack: agent loop + harness + memory + sub-agents. Worth more than any $500 vibe-coding course. Watch workshop today, then read article below.

Anthropic engineers just showed how to build agentic systems that run for days using "loops." "At Anthropic, >30% of our code is already written by loops - that's how we ship so fast. in this 40-minute workshop, they reveal the whole stack: agent loop + harness + memory + sub-agents. Worth more than any $500 vibe-coding course. Watch workshop today, then read article below.

Movez

521,024 次观看 • 4 个月前

Anthropic Engineer Andrej Karpathy just broke the entire premise of modern AI: "Agents aren't magic. They're distillation at scale." RAG → Graph RAG → Memory → Multimodal Agent Graphs. 99.99% of your LLM's capacity is wasted on garbage data it never needed. In a 20-minute conversation, Karpathy reveals the full reasoning stack Worth more than any $500 AI course you've seen this year.

Anthropic Engineer Andrej Karpathy just broke the entire premise of modern AI: "Agents aren't magic. They're distillation at scale." RAG → Graph RAG → Memory → Multimodal Agent Graphs. 99.99% of your LLM's capacity is wasted on garbage data it never needed. In a 20-minute conversation, Karpathy reveals the full reasoning stack Worth more than any $500 AI course you've seen this year.

Ricker

20,166 次观看 • 1 个月前

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below

Lunar

356,880 次观看 • 2 个月前

Anthropic Engineer Andrej Karpathy: "The biggest mistake in AI right now - people are forcing agents to work instead of mastering the harness engineering for model first We made that mistake in 2016 at OpenAI - It cost us 5 years " Opus 5.5 → Prompts → Agents → Graphs → Harness what Karpathy actually means: step 1 → stop forcing your agent to do everything, understand the model underneath first step 2 → demos are easy - products take a decade. self-driving proved it - if you skip the foundation, everything breaks step 3 → the agent is not the product. the foundation is. build that - and agents emerge on their own "you building agents right now - you're at the forefront. not OpenAI. not DeepMind. you " Watch it today before it gets buried Then read the full Opus 5.5 harness engineering guide below ↓

Anthropic Engineer Andrej Karpathy: "The biggest mistake in AI right now - people are forcing agents to work instead of mastering the harness engineering for model first We made that mistake in 2016 at OpenAI - It cost us 5 years " Opus 5.5 → Prompts → Agents → Graphs → Harness what Karpathy actually means: step 1 → stop forcing your agent to do everything, understand the model underneath first step 2 → demos are easy - products take a decade. self-driving proved it - if you skip the foundation, everything breaks step 3 → the agent is not the product. the foundation is. build that - and agents emerge on their own "you building agents right now - you're at the forefront. not OpenAI. not DeepMind. you " Watch it today before it gets buried Then read the full Opus 5.5 harness engineering guide below ↓

hayato

308,173 次观看 • 3 天前

Google engineer: “In 2026, if you aren’t building AI agents, it’s crazy how far behind you already are. At Google, 85% of our engineers were running self-improving agent harnesses.” In this 32-minute talk, a Google engineer with 30 years of experience explains what the future of agentic coding will look like. Worth more than 10 paid agent engineering courses. Watch it today, then read the guide below to build your first production-grade agent harness ↓

Google engineer: “In 2026, if you aren’t building AI agents, it’s crazy how far behind you already are. At Google, 85% of our engineers were running self-improving agent harnesses.” In this 32-minute talk, a Google engineer with 30 years of experience explains what the future of agentic coding will look like. Worth more than 10 paid agent engineering courses. Watch it today, then read the guide below to build your first production-grade agent harness ↓

Ichigo

137,768 次观看 • 1 个月前

Andrej Karpathy explained the 5 shifts that turned LLMs from chatbots into agentic systems: 00:00 - Memory turns chat into personal AI 6:41- Multimodal AI can read the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers This is not another video about “prompt engineering.” It is a 40-minute roadmap for the next AI workflow: memory / vision / reasoning / search / tools. Watch today, then read the article below on how to turn LLMs into self-improving agent loops.

Andrej Karpathy explained the 5 shifts that turned LLMs from chatbots into agentic systems: 00:00 - Memory turns chat into personal AI 6:41- Multimodal AI can read the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers This is not another video about “prompt engineering.” It is a 40-minute roadmap for the next AI workflow: memory / vision / reasoning / search / tools. Watch today, then read the article below on how to turn LLMs into self-improving agent loops.

Morlex

37,456 次观看 • 3 个月前

Creator of Claude Code: “I’m not prompting my agents anymore. I’m building "graphs" and "loops" - they’re building my agent. in 3-6 months, we’ll all be doing graph engineering for our agentic systems.” in 10-minute talk, Boris Cherny revealed what the future of agentic engineering will look like. worth more than a $500 agentic AI course. Watch it today, then read the full roadmap in the article below.

Creator of Claude Code: “I’m not prompting my agents anymore. I’m building "graphs" and "loops" - they’re building my agent. in 3-6 months, we’ll all be doing graph engineering for our agentic systems.” in 10-minute talk, Boris Cherny revealed what the future of agentic engineering will look like. worth more than a $500 agentic AI course. Watch it today, then read the full roadmap in the article below.

Codez

553,186 次观看 • 2 个月前

NVIDIA just dropped a 2.5-hour course on how to build coding agents, featuring the CTO of Cursor: 00:07 – self-driving codebases with async agents 37:50 – agentic AI, from the ground up 1:16:35 – context engineering for high-signal AI code reviews 1:53:26 – teach AI to code in any language Worth more than any $500 enterprise-AI course. Bookmark this & steal my harness, below.

NVIDIA just dropped a 2.5-hour course on how to build coding agents, featuring the CTO of Cursor: 00:07 – self-driving codebases with async agents 37:50 – agentic AI, from the ground up 1:16:35 – context engineering for high-signal AI code reviews 1:53:26 – teach AI to code in any language Worth more than any $500 enterprise-AI course. Bookmark this & steal my harness, below.

Phosphen

11,226 次观看 • 3 个月前

Andrej Karpathy : 10x engineers are normal. real agentic engineers are 100x this guy just shipped the playbook to become 100x context engineering. tool design. orchestrator-subagent. evals. the harness mindset. watch & bookmark it for this weekend

Andrej Karpathy : 10x engineers are normal. real agentic engineers are 100x this guy just shipped the playbook to become 100x context engineering. tool design. orchestrator-subagent. evals. the harness mindset. watch & bookmark it for this weekend

Avid

561,600 次观看 • 6 个月前

Andrej Karpathy just broke the entire premise of modern AI: "Agents aren't magic. They're distillation at scale." 99.99% of your LLM's capacity is wasted on garbage data it never needed. Small model + right tools + closed loop = terrifying capability. In a 16-minute conversation, Karpathy reveals the full reasoning stack. Worth more than any $500 AI course you've seen this year.

Andrej Karpathy just broke the entire premise of modern AI: "Agents aren't magic. They're distillation at scale." 99.99% of your LLM's capacity is wasted on garbage data it never needed. Small model + right tools + closed loop = terrifying capability. In a 16-minute conversation, Karpathy reveals the full reasoning stack. Worth more than any $500 AI course you've seen this year.

Morty

676,420 次观看 • 3 个月前