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 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... show more

Morlex

3,005 subscribers

37,456 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

19 条评论

纳米AI 的头像

纳米AI2 个月前

讲的真好，无剪辑、无字幕就一个Excalidraw白板讲看看国内的AI自媒体都讲的什么垃圾玩意

vartekx 的头像

vartekx2 个月前

tools turning LLMs into actual workers is the one that changes everything

Morlex 的头像

Morlex2 个月前

That's right mate

Spivach 的头像

Spivach2 个月前

The most interesting lectures are only from him, simple and short

Morty 的头像

Morty2 个月前

one of the best lesson in internet about LLM

Morlex 的头像

Morlex2 个月前

Yeah. Argee with you. What about your best topic of this video ?

Movez 的头像

Movez2 个月前

Wow. Haven’t seen this Andrew lecture before. Thx for the share, Morlex. Will watch today, then read the article.

Morlex 的头像

Morlex2 个月前

Thanks broski, i hope it's video will be useful

Sahil 的头像

Sahil2 个月前

Context is key. Andrej's shifts make sense in hindsight.

Dima T. 的头像

Dima T.2 个月前

Not another prompt engineering video" — then proceeds to explain 5 things that are basically architecture-level prompt engineering. Fair, though, that's the level that actually matters now

ViiTor AI 的头像

ViiTor AI2 个月前

Such an insightful summary! Karpathy’s videos have incredibly high information density, and localizing this content is no easy task. Followed, and looking forward to more of your edge notes on AI Agents!

SoSo004 的头像

SoSo0042 个月前

You should check out this Chrome extension called LingTube. It does voice translation and bilingual subtitles for YouTube, TikTok, Bilibili videos and more. Especially great for learning from tutorials, it's honestly saved me so much time 😊

Adel Bucetta 的头像

Adel Bucetta2 个月前

the real unlock is collapsing the time between idea and shipped product, but agentic systems are also forcing us to rethink what 'personal ai' even means in this context. memory isn't just a storage device anymore.

Nekt0 的头像

Nekt02 个月前

That seems like a fair take

Bounce 的头像

Bounce2 个月前

karpathy's 5 shifts framework is genuinely the map

Fadi Al-Majd 的头像

Fadi Al-Majd2 个月前

Five shifts to agentic AI. Egypt still can't keep the lights on in a lab though. UAE figured this out early. I want us building these locally, not importing them.

Karol Zdebel 的头像

Karol Zdebel2 个月前

memory is the one that quietly breaks things. once an agent remembers, a wrong fact from three sessions back poisons everything after and you can't trace where it came from. search and tools you can log, stale memory you can't.

Harry Tandy 的头像

Harry Tandy2 个月前

karpathy breaks this down so perfectly every single time

State of The Art™ - AI / AGI (e/acc) 的头像

State of The Art™ - AI / AGI (e/acc)2 个月前

Five shifts shaping LLMs today

相关视频

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

355,523 次观看 • 1 个月前

Anthropic Engineer Andrej Karpathy dropped a full 6-hour course on how to build LLMs from scratch and use it: • 00:00 - Deep dive into LLMs • 03:31:23 - Building ChatGPT from scratch • 05:27:43 - How to use LLMs (Karpathy method) This course can replace a $150K Stanford LLM senior degree. Start watching today, then read article below

Anthropic Engineer Andrej Karpathy dropped a full 6-hour course on how to build LLMs from scratch and use it: • 00:00 - Deep dive into LLMs • 03:31:23 - Building ChatGPT from scratch • 05:27:43 - How to use LLMs (Karpathy method) This course can replace a $150K Stanford LLM senior degree. Start watching today, then read article below

Morty

40,985 次观看 • 1 个月前

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m lecture: • 00:00 - understanding the different layers of AI memory • 30:00 - moving from simple LLM calls to AI agents • 50:00 - why agent systems are becoming a graph engineering problem • 1:12:00 - connecting context, tools and agent state • 1:24:00 - building a minimal agent harness from scratch • 1:46:00 - breaking down the architecture behind Hermes Agent • 2:08:00 - turning agent concepts into working systems 167-minute deep dive, and one of the clearest ways to understand how AI engineering is moving beyond prompts The progression: Prompt → Context → Memory → Agent → Loop → Graph → Agent Harness Watch it today, then read the full roadmap below

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m lecture: • 00:00 - understanding the different layers of AI memory • 30:00 - moving from simple LLM calls to AI agents • 50:00 - why agent systems are becoming a graph engineering problem • 1:12:00 - connecting context, tools and agent state • 1:24:00 - building a minimal agent harness from scratch • 1:46:00 - breaking down the architecture behind Hermes Agent • 2:08:00 - turning agent concepts into working systems 167-minute deep dive, and one of the clearest ways to understand how AI engineering is moving beyond prompts The progression: Prompt → Context → Memory → Agent → Loop → Graph → Agent Harness Watch it today, then read the full roadmap below

Morlex

51,558 次观看 • 1 个月前

Don't waste 2 years learning to use LLMs like Claude & ChatGPT. Andrej Karpathy, the godfather of AI, dropped a 2 hour course on how he personally uses LLMs daily. • 00:00 - LLMs simplified • 22:49 - which LLM to actually use • 42:00 - one prompt for full research • 1:13:57 - how to code with LLMs • 1:37:04 - NotebookLM podcast generation This course will teach you more about using LLMs than most AI engineers learn in their entire career. Bookmark this & give 2 hours today, no matter what. Then read the article below.

Don't waste 2 years learning to use LLMs like Claude & ChatGPT. Andrej Karpathy, the godfather of AI, dropped a 2 hour course on how he personally uses LLMs daily. • 00:00 - LLMs simplified • 22:49 - which LLM to actually use • 42:00 - one prompt for full research • 1:13:57 - how to code with LLMs • 1:37:04 - NotebookLM podcast generation This course will teach you more about using LLMs than most AI engineers learn in their entire career. Bookmark this & give 2 hours today, no matter what. Then read the article below.

Roan

56,500 次观看 • 1 个月前

Andrej Karpathy (Anthropic Team) dropped a full 7-hour course on "Intro and Deep Dive to LLMs and Tokenizer: • 00:00 - Intro to Large Language Models • 00:59:28 - Deep dive into LLMs (Karpathy method) • 03:31:43 - Let s build the GPT Tokenizer This Karpathy guide can replace a $100K Yale LLM senior degree. Start watching right now, then read article below

Andrej Karpathy (Anthropic Team) dropped a full 7-hour course on "Intro and Deep Dive to LLMs and Tokenizer: • 00:00 - Intro to Large Language Models • 00:59:28 - Deep dive into LLMs (Karpathy method) • 03:31:43 - Let s build the GPT Tokenizer This Karpathy guide can replace a $100K Yale LLM senior degree. Start watching right now, then read article below

Morty

44,481 次观看 • 1 个月前

Andrej Karpathy just rewrote the rules of using LLMs: "Prompting is going away. Delete everything, keep Graph." LLMs → Prompts → Agents → Graphs He dropped his full 2-hour course from Stanford on "Graph-Native Research" • 00:00 - Intro to Graph systems • 01:08:09 - LLMs architecture This Karpathy course can replace a $100K Yale LLM senior degree. Watch it today, then save the full graph engineering guide below

Andrej Karpathy just rewrote the rules of using LLMs: "Prompting is going away. Delete everything, keep Graph." LLMs → Prompts → Agents → Graphs He dropped his full 2-hour course from Stanford on "Graph-Native Research" • 00:00 - Intro to Graph systems • 01:08:09 - LLMs architecture This Karpathy course can replace a $100K Yale LLM senior degree. Watch it today, then save the full graph engineering guide below

Ricker

43,491 次观看 • 26 天前

Don't waste 2 years learning to use LLMs like Claude & ChatGPT. Andrej Karpathy one of the clearest minds in AI just released a 2‑hour breakdown of how he actually uses LLMs every day. • 00:00 — LLMs, explained like you’re busy • 22:49 — picking the right model (for real) • 42:00 — the single prompt that powers deep research • 1:13:57 — writing code with LLMs without the chaos • 1:37:04 — turning NotebookLM into a podcast machine If you watch this end to end, you’ll walk away with more practical LLM skill than many “AI engineers” collect over years. Save it. Carve out two hours today—no excuses. Then hit the article below.

Don't waste 2 years learning to use LLMs like Claude & ChatGPT. Andrej Karpathy one of the clearest minds in AI just released a 2‑hour breakdown of how he actually uses LLMs every day. • 00:00 — LLMs, explained like you’re busy • 22:49 — picking the right model (for real) • 42:00 — the single prompt that powers deep research • 1:13:57 — writing code with LLMs without the chaos • 1:37:04 — turning NotebookLM into a podcast machine If you watch this end to end, you’ll walk away with more practical LLM skill than many “AI engineers” collect over years. Save it. Carve out two hours today—no excuses. Then hit the article below.

CyrilXBT

51,835 次观看 • 1 个月前

Google Engineers just dropped a 1-hour course on agentic engineering from scratch: 0% - 00:00 – How to build your first AI agent 25% - 08:24 – Build agent memory (short, persistent, long) 50% - 28:34 – Agentic loops, long-running AI agents 100% - 1:00:22 – Multi-agentic systems This 1-hour guide will replace 10 paid agentic courses on the internet. Watch it today, then read how to run multiple agents in the article below.

Google Engineers just dropped a 1-hour course on agentic engineering from scratch: 0% - 00:00 – How to build your first AI agent 25% - 08:24 – Build agent memory (short, persistent, long) 50% - 28:34 – Agentic loops, long-running AI agents 100% - 1:00:22 – Multi-agentic systems This 1-hour guide will replace 10 paid agentic courses on the internet. Watch it today, then read how to run multiple agents in the article below.

Ricker

11,708 次观看 • 13 天前

Google just showed how AI engineers are moving from simple "RAG" to "graphs", memory and multimodal agents • 15:32 - setting up the production agent stack • 28:00 - turning disconnected data into a knowledge graph • 41:00 - Graph RAG with semantic + hybrid search • 58:00 - extracting graph context from images, text and video • 1:09:00 - orchestrating specialized agents with ADK • 1:20:00 - giving agents persistent memory across sessions 94-minute Google Cloud workshop, and it’s one of the clearest hands-on examples of the shift from -> RAG → Graph RAG → Memory → Multimodal Agent Graphs. The workshop uses Spanner Graph, Gemini, ADK and Memory Bank to build that stack. Watch it today, then read the full “From RAG to Context Graphs” roadmap below.

Google just showed how AI engineers are moving from simple "RAG" to "graphs", memory and multimodal agents • 15:32 - setting up the production agent stack • 28:00 - turning disconnected data into a knowledge graph • 41:00 - Graph RAG with semantic + hybrid search • 58:00 - extracting graph context from images, text and video • 1:09:00 - orchestrating specialized agents with ADK • 1:20:00 - giving agents persistent memory across sessions 94-minute Google Cloud workshop, and it’s one of the clearest hands-on examples of the shift from -> RAG → Graph RAG → Memory → Multimodal Agent Graphs. The workshop uses Spanner Graph, Gemini, ADK and Memory Bank to build that stack. Watch it today, then read the full “From RAG to Context Graphs” roadmap below.

Morlex

74,134 次观看 • 1 个月前

Google just released a free 1-hour lecture from Chief Scientist Jeff Dean on full AI Engineering. How to go from one LLM to coordinating 100 AI agents: 01:45 - Build an LLM from scratch 17:22 - Learn how to actually use AI models 30:03 - Master prompt engineering 52:35 - Coordinate 100 agents as one human Most people are still learning how to prompt one model. Jeff Dean is showing the full stack: LLMs → Prompts → Agents → Agent Teams → Graphs Prompting is the old workflow. Coordinating agent systems is the new one. This is 27 years of Google AI compressed into one hour. Bookmark and watch it today Then read the full Graph Engineering guide below ↓

Google just released a free 1-hour lecture from Chief Scientist Jeff Dean on full AI Engineering. How to go from one LLM to coordinating 100 AI agents: 01:45 - Build an LLM from scratch 17:22 - Learn how to actually use AI models 30:03 - Master prompt engineering 52:35 - Coordinate 100 agents as one human Most people are still learning how to prompt one model. Jeff Dean is showing the full stack: LLMs → Prompts → Agents → Agent Teams → Graphs Prompting is the old workflow. Coordinating agent systems is the new one. This is 27 years of Google AI compressed into one hour. Bookmark and watch it today Then read the full Graph Engineering guide below ↓

Lunar

102,011 次观看 • 1 个月前

Google just released a free 1-hour lecture from Chief Scientist Jeff Dean on full AI Engineering. How to go from one LLM to coordinating 100 AI agents: 0% → 01:45 - build an LLM from scratch 30% → 17:22 - learn how to actually use AI models 60% → 30:03 - master prompt engineering 100% → 52:35 - coordinate 100 agents as one human Most people are still learning how to prompt a single model. Jeff Dean is showing the entire stack: LLMs → Prompts → Agents → Agent Teams → Graphs Prompting is the old workflow. Coordinating entire agent systems is the next one. This is 27 years of Google AI compressed into a single hour. Bookmark it and watch today. Then read the full Graph Engineering guide below ↓

Google just released a free 1-hour lecture from Chief Scientist Jeff Dean on full AI Engineering. How to go from one LLM to coordinating 100 AI agents: 0% → 01:45 - build an LLM from scratch 30% → 17:22 - learn how to actually use AI models 60% → 30:03 - master prompt engineering 100% → 52:35 - coordinate 100 agents as one human Most people are still learning how to prompt a single model. Jeff Dean is showing the entire stack: LLMs → Prompts → Agents → Agent Teams → Graphs Prompting is the old workflow. Coordinating entire agent systems is the next one. This is 27 years of Google AI compressed into a single hour. Bookmark it and watch today. Then read the full Graph Engineering guide below ↓

Lunar

24,107 次观看 • 17 天前

Ex-Google Jeff Dean just dropped a 1-hour lecture on full AI engineering: from LLMs to Graphs 1:45 - LLM from scratch 17:22 - How to use AI models 30:03 - Prompt engineering 52:35 - One human coordinating 100 agents 27 years of building AI at Google, compressed into one hour. Watch it, then read the full guide on Graph engineering below.

Ex-Google Jeff Dean just dropped a 1-hour lecture on full AI engineering: from LLMs to Graphs 1:45 - LLM from scratch 17:22 - How to use AI models 30:03 - Prompt engineering 52:35 - One human coordinating 100 agents 27 years of building AI at Google, compressed into one hour. Watch it, then read the full guide on Graph engineering below.

Mahax

91,750 次观看 • 1 个月前

OpenAI senior engineer just released a 1-hour course on building agentic systems with Codex from scratch: • 00:36 - deep dive into Codex: agents, subagents • 11:34 - Codex agentic prompting patterns • 20:06 - long running Codex agents with /goal • 30:03 - building skills for Codex agents • 41:28 - self-improving loops with /automations this 1-hour workshop by the OpenAI team will replace a $500 AI engineering course watch today, then read how to build self-improving agentic systems with loops & graphs in the article below

OpenAI senior engineer just released a 1-hour course on building agentic systems with Codex from scratch: • 00:36 - deep dive into Codex: agents, subagents • 11:34 - Codex agentic prompting patterns • 20:06 - long running Codex agents with /goal • 30:03 - building skills for Codex agents • 41:28 - self-improving loops with /automations this 1-hour workshop by the OpenAI team will replace a $500 AI engineering course watch today, then read how to build self-improving agentic systems with loops & graphs in the article below

Codez

60,147 次观看 • 12 天前

Google just released a 1-hour course on “Context Engineering” for AI agents from scratch: • 00:00 - Introduction to “Context Engineering” • 03:02 - Context Engineering vs “prompting” • 16:18 - Build a context brain for your agent • 22:10 - Building agent context (tools, skills) • 29:06 - Agentic memory bank from scratch This 1-hour watch could replace a $500 course on agentic design. Watch it today, then read the full guide on Context Engineering in the article below.

Google just released a 1-hour course on “Context Engineering” for AI agents from scratch: • 00:00 - Introduction to “Context Engineering” • 03:02 - Context Engineering vs “prompting” • 16:18 - Build a context brain for your agent • 22:10 - Building agent context (tools, skills) • 29:06 - Agentic memory bank from scratch This 1-hour watch could replace a $500 course on agentic design. Watch it today, then read the full guide on Context Engineering in the article below.

Movez

14,822 次观看 • 1 个月前

Don't waste 2 years learning to build LLMs like Claude & ChatGPT. MIT dropped a 3 hour course on building LLMs from scratch for free. Training → Architecture → Scale. It covers everything about LLMs. • 00:00 - training an LLM • 1:20:46 - LLM architecture from scratch • 2:34:56 - scaling laws for LLMs Anthropic pays $750,000/year to AI engineers in 2026 who master this exact knowledge. Bookmark this & skip Netflix. Give it 4 hours today. Then read the article below.

Don't waste 2 years learning to build LLMs like Claude & ChatGPT. MIT dropped a 3 hour course on building LLMs from scratch for free. Training → Architecture → Scale. It covers everything about LLMs. • 00:00 - training an LLM • 1:20:46 - LLM architecture from scratch • 2:34:56 - scaling laws for LLMs Anthropic pays $750,000/year to AI engineers in 2026 who master this exact knowledge. Bookmark this & skip Netflix. Give it 4 hours today. Then read the article below.

Roan

85,865 次观看 • 1 个月前

My friend applied to 300 tech jobs in two years. No MIT. No Stanford. Last month Anthropic offered him $750,000. I asked him how he broke in from zero. He sent me the exact video that got him in. Andrej Karpathy's 3-hour course on building a full LLM from scratch. Anthropic's own researcher shows you how LLMs like ChatGPT & Claude are actually built. I watched it last night. Halfway through, I realized it's embarrassingly simple to break into an AI lab. Bookmark this and read the article below. • 00:00 - intro to LLMs • 12:41 - LLM training pipeline • 31:58 - LLM tools & plugins • 41:14 - LLM transformer architecture • 2:19:02 - scaling the LLM

My friend applied to 300 tech jobs in two years. No MIT. No Stanford. Last month Anthropic offered him $750,000. I asked him how he broke in from zero. He sent me the exact video that got him in. Andrej Karpathy's 3-hour course on building a full LLM from scratch. Anthropic's own researcher shows you how LLMs like ChatGPT & Claude are actually built. I watched it last night. Halfway through, I realized it's embarrassingly simple to break into an AI lab. Bookmark this and read the article below. • 00:00 - intro to LLMs • 12:41 - LLM training pipeline • 31:58 - LLM tools & plugins • 41:14 - LLM transformer architecture • 2:19:02 - scaling the LLM

Roan

287,470 次观看 • 2 个月前

Google just dropped a 1-hour course on how to become an AI engineer in 2026: • 00:00 - Context engineering • 10:00 - How to build, deploy, and run AI agents • 31:52 - Agentic loops, long-running AI agents • 43:22 - Building MCP from scratch • 51:20 - Prompt engineering • 59:10 - AI development trends This 1-hour watch will replace a $500 AI engineering course. Watch it today, then read the article below.

Google just dropped a 1-hour course on how to become an AI engineer in 2026: • 00:00 - Context engineering • 10:00 - How to build, deploy, and run AI agents • 31:52 - Agentic loops, long-running AI agents • 43:22 - Building MCP from scratch • 51:20 - Prompt engineering • 59:10 - AI development trends This 1-hour watch will replace a $500 AI engineering course. Watch it today, then read the article below.

Aria Westcott

26,526 次观看 • 1 个月前

Google just dropped a 1-hour course on how to become an AI engineer in 2026: • 00:00 - Context engineering • 10:00 - How to build, deploy, and run AI agents • 31:52 - Agentic loops, long-running AI agents • 43:22 - Building MCP from scratch • 51:20 - Prompt engineering • 59:10 - AI development trends This 1-hour watch will replace a $500 AI engineering course. Watch it today, then read the full pipeline in the article below.

Google just dropped a 1-hour course on how to become an AI engineer in 2026: • 00:00 - Context engineering • 10:00 - How to build, deploy, and run AI agents • 31:52 - Agentic loops, long-running AI agents • 43:22 - Building MCP from scratch • 51:20 - Prompt engineering • 59:10 - AI development trends This 1-hour watch will replace a $500 AI engineering course. Watch it today, then read the full pipeline in the article below.

Codez

188,089 次观看 • 2 个月前

Don't waste 2 years figuring out how AI agents actually work. ex. Anthropic & Google engineers at Stanford just dropped a 1-hour lecture on self-improving AI agents: • 00:00 - Introduction to self-learning AI systems • 31:22 - inside a LLM: self-correction, backtracking • 42:24 - goal → loops → graphs→ feedback: the Agent loop • 45:47 - 6 agent orchestration patterns • 50:37 - the generator-verifier gap - why self-improvement stalls Planning, multi-step reasoning, self-correction. That's the entire agent roadmap for 2026. Bookmark this & give 70 minutes today. Then read the article below.

Don't waste 2 years figuring out how AI agents actually work. ex. Anthropic & Google engineers at Stanford just dropped a 1-hour lecture on self-improving AI agents: • 00:00 - Introduction to self-learning AI systems • 31:22 - inside a LLM: self-correction, backtracking • 42:24 - goal → loops → graphs→ feedback: the Agent loop • 45:47 - 6 agent orchestration patterns • 50:37 - the generator-verifier gap - why self-improvement stalls Planning, multi-step reasoning, self-correction. That's the entire agent roadmap for 2026. Bookmark this & give 70 minutes today. Then read the article below.

Movez

40,448 次观看 • 1 个月前

OpenAI just launched a 3-hour course on building agentic systems from scratch: 00:00 - Building workspace agents 37:42 - Deep dive into OpenAI AgentKit 1:24:01 - Agent memory (loops, context, evals) 2:21:44 - Agentic training (OpenAI playbook) This 3-hour watch will replace you 10 paid agentic courses. Watch it today, then learn how to build a team of AI agents from scratch in the article below.

OpenAI just launched a 3-hour course on building agentic systems from scratch: 00:00 - Building workspace agents 37:42 - Deep dive into OpenAI AgentKit 1:24:01 - Agent memory (loops, context, evals) 2:21:44 - Agentic training (OpenAI playbook) This 3-hour watch will replace you 10 paid agentic courses. Watch it today, then learn how to build a team of AI agents from scratch in the article below.

Codez

79,345 次观看 • 2 个月前