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: "Prompting is going away. Delete everything, keep Graph." In 69 minutes he shows how to build Graphs, and why it's the only thing that will be left standing at the end Prompts → Agents → Loops → Graphs a loop keeps one agent working until the job... show more

Callan

1,124 subscribers

493,407 次观看 • 4 天前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

27 条评论

Chris S. 的头像

Chris S.3 天前

The truth is that you don't need to know any of this. You just give opus a task or access to your issues and it will loop and work and fix and do it all.

Harley Lewis Foote 的头像

Harley Lewis Foote3 天前

69 minutes to discover that a graph is just a loop with a mortgage. we've had dags for decades.

Internet Labs 的头像

Internet Labs3 天前

sometimes i think maybe prompt engineering was always just a temporary fix for missing structure.

Neil Brown 的头像

Neil Brown4 天前

Quite like the process trees in Erlang that was running telephone exchanges in the 90’s

VkDream 的头像

VkDream4 天前

提示词工程这个词还没捂热就要进历史博物馆了

Maxine Lai 的头像

Maxine Lai4 天前

I don’t want to learn, will it be built-in to Claude Code harness itself?

clogwog 的头像

clogwog3 天前

@grok how old is this video?

Stefan Bösch / CaptainCarlos 的头像

Stefan Bösch / CaptainCarlos3 天前

The legend himself speaks at Stanford. 69 minutes. Even the runtime is legendary. Talk is cheap. Show me the code. Code is cheap. Show me the prompt. Prompts are cheap. Show me the agent. Agents are cheap. Show me the loops. Loops are cheap. Show me the graph.

Blum 的头像

Blum2 天前

Can’t pass up 69 minutes of Karpathy. Bookmarked!

Hussain Hashim | Building SundayBack 的头像

Hussain Hashim | Building SundayBack3 天前

@callanxai loops need clear stop conditions. Learned the hard way: endless loops eat time and resources.

Janoyl Anitt 的头像

Janoyl Anitt3 天前

Link to the actual video?

Shawn McAllister 的头像

Shawn McAllister3 天前

I built this and am continuing to evolve it.

Grzegorz 'Gera' Riabov 的头像

Grzegorz 'Gera' Riabov3 天前

@grok расскажи всем что этот аккаунт и подобные им рассказывают неправду. Карпаты такого не говорит и такого пайплайна не предлагал. В видео старая лекция Карпаты в стендфорде

Scott Goodyear 的头像

Scott Goodyear3 天前

lol why would you listen to a guy who worked on tesla autopilot of all things? It's late to a promise that it would be driving autonomously 2 years ago

Walter Richard 的头像

Walter Richard3 天前

@grok does this video talk at all about graph or is the caption misleading

dr. Djakdekiel 的头像

dr. Djakdekiel3 天前

Another bullshit

Jonathan Vitela 的头像

Jonathan Vitela3 天前

Seems as if there will always be something new with this process.

Stefan Bösch / CaptainCarlos 的头像

Stefan Bösch / CaptainCarlos3 天前

Prompts are cheap. Show me the agent. Agents are cheap. Show me the loops. Loops are cheap. Show me the graph.

IrradiatedFentOwl 的头像

IrradiatedFentOwl3 天前

This guy is the goat

Stevo Changa 的头像

Stevo Changa3 天前

Yes trying this next :)

Scott Goodyear 的头像

Scott Goodyear3 天前

oh my god this explains why imagenet is labeled so terribly, there are babies labeled as croquet balls all over the place

Raunak Yadush 的头像

Raunak Yadush3 天前

The real shift is from prompting individual models to designing systems that coordinate them. Graphs make that transition much more interesting.

Brian D. Evans 的头像

Brian D. Evans3 天前

Everyone still stuck on prompts

heath 的头像

heath3 天前

“delete everything, keep Graph” is an insanely good line lol now I want to see the full breakdown

Everplay Tech 的头像

Everplay Tech3 天前

This is a joke right ? This is worse than illiteracy. The idea is maddening to think the goal is a single loop - this is SLOP INCARNATE

PersonaStack.ai 的头像

PersonaStack.ai3 天前

Whats after graphs is automatic graphs, and there's already a cloud platform for it.

Mark Arguinbaev 的头像

Mark Arguinbaev3 天前

We are doing something similar with Mergestorm in terms of allowing you to create a large 10+ PR plan with a dependency graph, then your agent fires them through the pipeline one by one.

相关视频

Andrej Karpathy: "prompting is going away, delete everything and keep the graph." in 1 hour he breaks down how to build graphs from scratch, make your agents work and improve themselves. not the newest session, but still one of the best you can find. watch it, then read the full guide on graphs below.

Andrej Karpathy: "prompting is going away, delete everything and keep the graph." in 1 hour he breaks down how to build graphs from scratch, make your agents work and improve themselves. not the newest session, but still one of the best you can find. watch it, then read the full guide on graphs below.

Anatoli Kopadze

306,526 次观看 • 1 个月前

Google Brain founder, Andrew Ng: "Prompting will die in 6 months. Loops and graphs are what's replacing it." In 97 minutes he shows how to build agents that plan, execute and improve without you Prompts → Agents → Loops → Graphs a loop closes one job without you sitting there a graph decides which jobs exist and carries every accepted one into the next run most people are still getting better at the part he gives six months watch it today, then save the full guide on loops and graphs below ↓

Google Brain founder, Andrew Ng: "Prompting will die in 6 months. Loops and graphs are what's replacing it." In 97 minutes he shows how to build agents that plan, execute and improve without you Prompts → Agents → Loops → Graphs a loop closes one job without you sitting there a graph decides which jobs exist and carries every accepted one into the next run most people are still getting better at the part he gives six months watch it today, then save the full guide on loops and graphs below ↓

Callan

78,601 次观看 • 6 天前

Anthropic engineer: "At Anthropic we don't write prompts anymore. We build loops and graphs." In 29 minutes she shows how Anthropic builds agents that remember, fix their own mistakes and get sharper every run Prompts → Agents → Loops → Graphs a loop catches the mistake and sends it back to the step that made it a graph keeps what worked and hands it to the next run as a rule the first half is the part people build, the second is the part almost nobody does watch it today, then save the full graph engineering guide below ↓

Anthropic engineer: "At Anthropic we don't write prompts anymore. We build loops and graphs." In 29 minutes she shows how Anthropic builds agents that remember, fix their own mistakes and get sharper every run Prompts → Agents → Loops → Graphs a loop catches the mistake and sends it back to the step that made it a graph keeps what worked and hands it to the next run as a rule the first half is the part people build, the second is the part almost nobody does watch it today, then save the full graph engineering guide below ↓

Callan

58,649 次观看 • 5 天前

OpenAI CEO, Sam Altman: "You don't need to write prompts anymore. You need Loops and Graphs." In 38 minutes he explains why his own engineers stopped writing prompts, and what they build instead Prompts → Agents → Loops → Graphs a prompt buys you one answer a graph buys you the whole job, and you are not in it watch it today then save the full graph engineering guide below before everyone catches up ↓

OpenAI CEO, Sam Altman: "You don't need to write prompts anymore. You need Loops and Graphs." In 38 minutes he explains why his own engineers stopped writing prompts, and what they build instead Prompts → Agents → Loops → Graphs a prompt buys you one answer a graph buys you the whole job, and you are not in it watch it today then save the full graph engineering guide below before everyone catches up ↓

Hanako

17,768 次观看 • 1 个月前

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to an agent graph that builds itself: 10:16 - Build your first AI agent 41:05 - Master prompt engineering 54:45 - Turn agents into graphs 1:20:10 - Run loops inside agent graphs 1:43:33 - Build a graph that builds itself Most people ship one agent and stop there. Google is teaching everything after: Prompt → Agents → Graphs → Loops → Self-Building Systems Single agents are the old workflow. Graphs that evolve themselves are the new one. This 2-hour watch is worth more than most paid agent engineering courses. Bookmark and watch it today Then read how to run 1,000 agents from one prompt below ↓

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to an agent graph that builds itself: 10:16 - Build your first AI agent 41:05 - Master prompt engineering 54:45 - Turn agents into graphs 1:20:10 - Run loops inside agent graphs 1:43:33 - Build a graph that builds itself Most people ship one agent and stop there. Google is teaching everything after: Prompt → Agents → Graphs → Loops → Self-Building Systems Single agents are the old workflow. Graphs that evolve themselves are the new one. This 2-hour watch is worth more than most paid agent engineering courses. Bookmark and watch it today Then read how to run 1,000 agents from one prompt below ↓

Lunar

52,359 次观看 • 1 个月前

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to an agent graph that can build itself: 0% → 10:16 - build your first AI agent 25% → 41:05 - master prompt engineering 50% → 54:45 - turn agents into graphs 75% → 1:20:10 - run loops inside agent graphs 100% → 1:43:33 - build a graph that builds itself Most people build one agent and stop there. Google is teaching everything that comes after: Prompt → Agents → Graphs → Loops → Self-Building Systems Single agents are the old workflow. Graphs that evolve themselves are the next one. This 2-hour course is worth more than most paid agent engineering courses. Bookmark it and watch today Then read how to run 1,000 agents from one prompt below ↓

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to an agent graph that can build itself: 0% → 10:16 - build your first AI agent 25% → 41:05 - master prompt engineering 50% → 54:45 - turn agents into graphs 75% → 1:20:10 - run loops inside agent graphs 100% → 1:43:33 - build a graph that builds itself Most people build one agent and stop there. Google is teaching everything that comes after: Prompt → Agents → Graphs → Loops → Self-Building Systems Single agents are the old workflow. Graphs that evolve themselves are the next one. This 2-hour course is worth more than most paid agent engineering courses. Bookmark it and watch today Then read how to run 1,000 agents from one prompt below ↓

Lunar

44,744 次观看 • 24 天前

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents running inside one graph: 17:44 - Build your first AI agent 39:30 - Run agents with loop engineering 1:12:38 - Turn agent loops into graphs 1:34:26 - Build agents that throttle themselves 1:55:05 - Orchestrate the full multi-agent system Most people build one agent and stop there. Google is teaching the full stack: Prompt → Agents → Loops → Graphs → Multi-Agent Systems Single agents are the old workflow. Self-regulating agent graphs are the new one. This 2-hour watch is worth more than most paid agent engineering courses. Bookmark and watch it today Then read the full architecture below ↓

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents running inside one graph: 17:44 - Build your first AI agent 39:30 - Run agents with loop engineering 1:12:38 - Turn agent loops into graphs 1:34:26 - Build agents that throttle themselves 1:55:05 - Orchestrate the full multi-agent system Most people build one agent and stop there. Google is teaching the full stack: Prompt → Agents → Loops → Graphs → Multi-Agent Systems Single agents are the old workflow. Self-regulating agent graphs are the new one. This 2-hour watch is worth more than most paid agent engineering courses. Bookmark and watch it today Then read the full architecture below ↓

Lunar

403,431 次观看 • 1 个月前

Google just released free 2-hour course on full Graph engineering: 1 prompt → 100 agents → loops → graphs from 0% to 100%: 10% → 17:44 - build your first agent 30% → 39:30 - Loop engineering: iterate, check, break 60% → 1:12:38 - Graph engineering 75% → 1:34:26 - agents that throttle themselves 100% → 1:55:05 - full graph for multi-agentic systems everyone builds one agent and calls it done - this is the full system where agents wire themselves into a graph watch the course, build the graph - then read the full architecture below ↓

Google just released free 2-hour course on full Graph engineering: 1 prompt → 100 agents → loops → graphs from 0% to 100%: 10% → 17:44 - build your first agent 30% → 39:30 - Loop engineering: iterate, check, break 60% → 1:12:38 - Graph engineering 75% → 1:34:26 - agents that throttle themselves 100% → 1:55:05 - full graph for multi-agentic systems everyone builds one agent and calls it done - this is the full system where agents wire themselves into a graph watch the course, build the graph - then read the full architecture below ↓

codila

467,749 次观看 • 2 个月前

Google Brain founder, Andrew Ng: "Prompting will be dead in 6 months. Loops and graphs are replacing it." in 100 minutes at Stanford he shows how to build agents that finish the work and sharpen themselves LLMs → Agents → Loops → Graphs the first 15 minutes go past where most $500 AI courses stop most people are still learning prompts while the leverage moved two layers up same model, same tokens, and the only thing that changes is the shape you run it in watch the lecture today, then save the full graph engineering guide below

Google Brain founder, Andrew Ng: "Prompting will be dead in 6 months. Loops and graphs are replacing it." in 100 minutes at Stanford he shows how to build agents that finish the work and sharpen themselves LLMs → Agents → Loops → Graphs the first 15 minutes go past where most $500 AI courses stop most people are still learning prompts while the leverage moved two layers up same model, same tokens, and the only thing that changes is the shape you run it in watch the lecture today, then save the full graph engineering guide below

Hanako

121,441 次观看 • 1 个月前

Google just released free 2-hour course on full Graph engineering: 1 prompt → agent teams → loops → graphs from 0% to 100%: 10% → 10:16 - build your first agent 40% → 41:05 - Prompt engineering 50% → 54:45 - Graph engineering 75% → 1:20:10 - Loop engineering (with graphs) 100% → 1:43:33 - the graph that builds itself most people ship one agent and stop - this is everything after watch it today - then read how to run 1000 agents from one prompt below ↓

Google just released free 2-hour course on full Graph engineering: 1 prompt → agent teams → loops → graphs from 0% to 100%: 10% → 10:16 - build your first agent 40% → 41:05 - Prompt engineering 50% → 54:45 - Graph engineering 75% → 1:20:10 - Loop engineering (with graphs) 100% → 1:43:33 - the graph that builds itself most people ship one agent and stop - this is everything after watch it today - then read how to run 1000 agents from one prompt below ↓

codila

105,921 次观看 • 1 个月前

Anthropic engineer: "At Anthropic, all of our engineers are running hundreds of agents The way you do it is graph engineering" In just 36 minutes, he shows how Anthropic runs hundreds of agents at once and what actually makes it possible Prompts → Agents → Loops → Graphs The part most people skip is the return path, where every accepted result becomes a constraint for the next run Same model, same tokens, completely different system Prompting is the old workflow Graph engineering is the next one Watch it today Then save the full graph engineering guide below before everyone starts catching up ↓

Anthropic engineer: "At Anthropic, all of our engineers are running hundreds of agents The way you do it is graph engineering" In just 36 minutes, he shows how Anthropic runs hundreds of agents at once and what actually makes it possible Prompts → Agents → Loops → Graphs The part most people skip is the return path, where every accepted result becomes a constraint for the next run Same model, same tokens, completely different system Prompting is the old workflow Graph engineering is the next one Watch it today Then save the full graph engineering guide below before everyone starts catching up ↓

Lunar

32,836 次观看 • 21 天前

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents running inside a single graph: 0% → 17:44 - build your first AI agent 25% → 39:30 - run agents with loop engineering 50% → 1:12:38 - turn agent loops into graphs 75% → 1:34:26 - build agents that regulate themselves 100% → 1:55:05 - orchestrate the entire multi-agent system Most people build one agent and stop there. Google is teaching the entire stack: Prompt → Agents → Loops → Graphs → Multi-Agent Systems Single agents are the old workflow. Self-regulating agent graphs are the next one. This 2-hour course is worth more than most paid agent engineering courses. Bookmark it and watch today Then read the full architecture below ↓

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents running inside a single graph: 0% → 17:44 - build your first AI agent 25% → 39:30 - run agents with loop engineering 50% → 1:12:38 - turn agent loops into graphs 75% → 1:34:26 - build agents that regulate themselves 100% → 1:55:05 - orchestrate the entire multi-agent system Most people build one agent and stop there. Google is teaching the entire stack: Prompt → Agents → Loops → Graphs → Multi-Agent Systems Single agents are the old workflow. Self-regulating agent graphs are the next one. This 2-hour course is worth more than most paid agent engineering courses. Bookmark it and watch today Then read the full architecture below ↓

Lunar

12,020 次观看 • 28 天前

Google just dropped a 1-hour course on full AI engineering: from 1 agent to Loops and Graphs 7:02 - Build your first agent 13:34 - What agents can do 23:08 - Context engineering 32:56 - Graph engineering 54:11 - Full autonomous system One agent saves you an hour. A thousand replaces the team. Watch it, then read the full guide on loops and graphs below

Google just dropped a 1-hour course on full AI engineering: from 1 agent to Loops and Graphs 7:02 - Build your first agent 13:34 - What agents can do 23:08 - Context engineering 32:56 - Graph engineering 54:11 - Full autonomous system One agent saves you an hour. A thousand replaces the team. Watch it, then read the full guide on loops and graphs below

Mahax

40,518 次观看 • 1 个月前

Anthropic engineer: "90% of our engineers were already running self-improving loops Now everyone is moving toward agentic graphs" "Prompting is basically finished" In just 10 minutes, she builds her complete Claude Code setup live from an empty terminal Agents → Loops → Graphs → Self-Improving Systems Prompting was the old workflow Graph engineering is the next one This 10-minute breakdown is worth more than most $1,000 agent engineering courses Watch it today Then save the full guide below before everyone catches on ↓

Anthropic engineer: "90% of our engineers were already running self-improving loops Now everyone is moving toward agentic graphs" "Prompting is basically finished" In just 10 minutes, she builds her complete Claude Code setup live from an empty terminal Agents → Loops → Graphs → Self-Improving Systems Prompting was the old workflow Graph engineering is the next one This 10-minute breakdown is worth more than most $1,000 agent engineering courses Watch it today Then save the full guide below before everyone catches on ↓

rari

203,086 次观看 • 1 个月前

Anthropic engineer: "You don't need to babysit agents. You need Loops and Graphs that run them for you." In 30 minutes, he shows exactly what the Anthropic engineers build so agents run without them, and how to start building it yourself. The missing piece most people skip: how to wire those agents into a graph that self-corrects every run. Watch it, then read the full guide on loops and graphs below.

Anthropic engineer: "You don't need to babysit agents. You need Loops and Graphs that run them for you." In 30 minutes, he shows exactly what the Anthropic engineers build so agents run without them, and how to start building it yourself. The missing piece most people skip: how to wire those agents into a graph that self-corrects every run. Watch it, then read the full guide on loops and graphs below.

Mahax

85,343 次观看 • 1 个月前

Andrew Ng just released a free 2-hour course on complete Graph Engineering How to go from one prompt to 100 agents that loop, improve, 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 finished Andrew Ng is already teaching everything that comes next: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow Systems that improve and run without you are the next one This 2-hour course is worth more than most $500 agent engineering programs Bookmark it and watch before everyone catches up Then read how to run 1,000 agents from one prompt below ↓

Andrew Ng just released a free 2-hour course on complete Graph Engineering How to go from one prompt to 100 agents that loop, improve, 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 finished Andrew Ng is already teaching everything that comes next: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow Systems that improve and run without you are the next one This 2-hour course is worth more than most $500 agent engineering programs Bookmark it and watch before everyone catches up Then read how to run 1,000 agents from one prompt below ↓

reira

14,729 次观看 • 29 天前

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

226,659 次观看 • 1 个月前

Anthropic engineer: "90% of our engineers were already running self-improving loops Now everyone is building agentic graphs" "Prompting is basically over" In just 10 minutes, she builds her complete Claude Code system live from an empty terminal Agents → Loops → Graphs → Self-Improving Systems Prompting was the old workflow Graph engineering is the new one This 10-minute video is worth more than most $1,000 agent engineering courses Watch it today Then save the full guide below before everyone catches up ↓

Anthropic engineer: "90% of our engineers were already running self-improving loops Now everyone is building agentic graphs" "Prompting is basically over" In just 10 minutes, she builds her complete Claude Code system live from an empty terminal Agents → Loops → Graphs → Self-Improving Systems Prompting was the old workflow Graph engineering is the new one This 10-minute video is worth more than most $1,000 agent engineering courses Watch it today Then save the full guide below before everyone catches up ↓

Lunar

530,728 次观看 • 3 天前

Sam Altman (CEO of OpenAI): "You don't need to write prompts anymore. You need loops and graphs that write them for you." in 78 minutes he explains how to use LLMs better than almost anyone does Prompts → Agents → Loops → Graphs that is the whole difference between using AI and having AI work for you same model, same tokens, and the only thing that changes is the shape you run it in watch it today, then save the full graph engineering guide below

Sam Altman (CEO of OpenAI): "You don't need to write prompts anymore. You need loops and graphs that write them for you." in 78 minutes he explains how to use LLMs better than almost anyone does Prompts → Agents → Loops → Graphs that is the whole difference between using AI and having AI work for you same model, same tokens, and the only thing that changes is the shape you run it in watch it today, then save the full graph engineering guide below

Hanako

289,557 次观看 • 25 天前

Google engineer: "We don't prompt agents anymore. We build Loops and Graphs that prompt them for us." In 30 minutes he shows how they build agents at Google that do all the work, and why Loops are what make it possible. The missing piece most people skip: you're not supposed to talk to your agents. You're supposed to build the Loop that does. Watch it, then read the full guide on loops and graphs below

Google engineer: "We don't prompt agents anymore. We build Loops and Graphs that prompt them for us." In 30 minutes he shows how they build agents at Google that do all the work, and why Loops are what make it possible. The missing piece most people skip: you're not supposed to talk to your agents. You're supposed to build the Loop that does. Watch it, then read the full guide on loops and graphs below

Mahax

28,167 次观看 • 1 个月前