Загрузка видео...

Не удалось загрузить видео

На главную

Andrej Karpathy spent 70 minutes explaining how top AI users actually work with LLMs. And most people are overcomplicating it. Bookmark it for later.

agentsmaxxing's profile picture

ai maxxer

1,488 subscribers

331,996 просмотров • 20 дней назад •via X (Twitter)

Наука и технологииОбразованиеНовости и политика
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Andrej Karpathy recorded 70 minutes Breaking down how top AI users actually work with LLMs And most people are making it way too complicated Worth more than most $300 AI courses Bookmark and watch it later
1:09:52

Andrej Karpathy recorded 70 minutes Breaking down how top AI users actually work with LLMs And most people are making it way too complicated Worth more than most $300 AI courses Bookmark and watch it later

rari

111,061 просмотров • 18 дней назад

ANDREJ KARPATHY WAS RIGHT. THIS 40-MINUTE Y COMBINATOR LECTURE PROVES IT we're in the 1960s of LLMs most people using Claude have the wrong mental model Software 3.0. LLMs as operating systems how to actually think about and work with them save this 👇
37:37

ANDREJ KARPATHY WAS RIGHT. THIS 40-MINUTE Y COMBINATOR LECTURE PROVES IT we're in the 1960s of LLMs most people using Claude have the wrong mental model Software 3.0. LLMs as operating systems how to actually think about and work with them save this 👇

Mr. Buzzoni

327,392 просмотров • 3 месяцев назад

Anthropic Engineer Andrej Karpathy: "LLM models writes code - and now it writes it better than you." Now LLMs write 70–90% of production code at top AI labs. Agents need the same thing: a loop that verifies its own output. No baseline = no benchmark = no improvement. In this 15-min talk, Karpathy breaks down how AI models actually works.
10:30

Anthropic Engineer Andrej Karpathy: "LLM models writes code - and now it writes it better than you." Now LLMs write 70–90% of production code at top AI labs. Agents need the same thing: a loop that verifies its own output. No baseline = no benchmark = no improvement. In this 15-min talk, Karpathy breaks down how AI models actually works.

Ricker

11,347 просмотров • 9 дней назад

Ilya Sutskever spent 5 minutes in 2015 explaining the exact trajectory of AI models. He was completely right. Most people will scroll past this. Don't be most people. Watch & Bookmark it for this weekend:
5:26

Ilya Sutskever spent 5 minutes in 2015 explaining the exact trajectory of AI models. He was completely right. Most people will scroll past this. Don't be most people. Watch & Bookmark it for this weekend:

Chidanand Tripathi

52,590 просмотров • 3 месяцев назад

Andrej Karpathy builds a personal wiki to think with LLMs. I took that idea and went further. Claude Code + Obsidian = an AI that actually knows you. Your goals. Your context. Your history. Not a chatbot. A second brain that remembers. Here's exactly how to build it:
1:48

Andrej Karpathy builds a personal wiki to think with LLMs. I took that idea and went further. Claude Code + Obsidian = an AI that actually knows you. Your goals. Your context. Your history. Not a chatbot. A second brain that remembers. Here's exactly how to build it:

leopardracer

222,145 просмотров • 3 месяцев назад

KARPATHY WAS RIGHT. THIS 40-MINUTE Y COMBINATOR LECTURE PROVES IT Karpathy said we're in the 1960s of AI - most people using Claude Opus 4.8 are still acting like it's just a search engine > software 3.0 - LLMs as operating systems, not chatbots > autonomous agents that run entire workflows without you watching the 32 skills in this article are how you actually cross that line bookmark this 👇
37:18

KARPATHY WAS RIGHT. THIS 40-MINUTE Y COMBINATOR LECTURE PROVES IT Karpathy said we're in the 1960s of AI - most people using Claude Opus 4.8 are still acting like it's just a search engine > software 3.0 - LLMs as operating systems, not chatbots > autonomous agents that run entire workflows without you watching the 32 skills in this article are how you actually cross that line bookmark this 👇

Mr. Buzzoni

566,670 просмотров • 2 месяцев назад

Andrej Karpathy in 1 hour reveal how he actually works with AI: "i just tell the machine what i want, in plain words" no prompt frameworks. no 40-line system prompts. no magic. by 2026 the engineer who dismisses LLMs loses to the junior who configured one right 1 hour. free. the most honest look at how the best in the world actually uses AI bookmark & watch
1:00:11

Andrej Karpathy in 1 hour reveal how he actually works with AI: "i just tell the machine what i want, in plain words" no prompt frameworks. no 40-line system prompts. no magic. by 2026 the engineer who dismisses LLMs loses to the junior who configured one right 1 hour. free. the most honest look at how the best in the world actually uses AI bookmark & watch

Morty

285,860 просмотров • 1 месяц назад

OpenAI co-founder Andrej Karpathy: "You literally have to put in 10,000 hours to learn Claude" 11-min workshop from Goat of AI - how he's actually uses it He reveales all the features that he use in this video bookmark & watch - the most prodactive way for your evening
11:23

OpenAI co-founder Andrej Karpathy: "You literally have to put in 10,000 hours to learn Claude" 11-min workshop from Goat of AI - how he's actually uses it He reveales all the features that he use in this video bookmark & watch - the most prodactive way for your evening

Morty

118,913 просмотров • 1 месяц назад

Stop video editing. AI can create viral shorts in 5 minutes. Here's how easy it is: [Bookmark for later]
0:27

Stop video editing. AI can create viral shorts in 5 minutes. Here's how easy it is: [Bookmark for later]

Shushant Lakhyani

290,577 просмотров • 2 лет назад

Andrej Karpathy just exposed how LLMs actually thinks: "LLMs don't want to succeed. They want to imitate." It has 80 transformer layers and spends the SAME compute on every single token as your brain In a 45-minute talk at Microsoft Build, Karpathy reveals the full psychology of LLMs. Worth more than any $500 prompting course you've seen on your timeline.
41:53

Andrej Karpathy just exposed how LLMs actually thinks: "LLMs don't want to succeed. They want to imitate." It has 80 transformer layers and spends the SAME compute on every single token as your brain In a 45-minute talk at Microsoft Build, Karpathy reveals the full psychology of LLMs. Worth more than any $500 prompting course you've seen on your timeline.

Morty

139,031 просмотров • 25 дней назад

Andrej Karpathy spent 4 minutes in an interview explaining a single idea about how most people haven’t even started learning how to use AI and everyone paying $20/month for a subscription.. that's not really using Claude at all his point is that the real skill gap is the ability to build with AI he identified 4 behaviors that break Claude Code and put them all into one file a developer expanded it into 21 rules and published it - 82,000 stars and #1 on GitHub Trending coding accuracy jumped from 65% to 94% here's what these 21 rules actually are and why most developers using Claude every day have never configured them the full breakdown is covered in the article below 👇
4:19

Andrej Karpathy spent 4 minutes in an interview explaining a single idea about how most people haven’t even started learning how to use AI and everyone paying $20/month for a subscription.. that's not really using Claude at all his point is that the real skill gap is the ability to build with AI he identified 4 behaviors that break Claude Code and put them all into one file a developer expanded it into 21 rules and published it - 82,000 stars and #1 on GitHub Trending coding accuracy jumped from 65% to 94% here's what these 21 rules actually are and why most developers using Claude every day have never configured them the full breakdown is covered in the article below 👇

rewind

3,193,285 просмотров • 2 месяцев назад

HOW AI AGENTS ACTUALLY WORK. 20 minutes. clearer than any course you've paid for. Bookmark this. watch it tonight. full breakdown of both Claude Agent Teams and Kimi Agent Swarm below.
20:29

HOW AI AGENTS ACTUALLY WORK. 20 minutes. clearer than any course you've paid for. Bookmark this. watch it tonight. full breakdown of both Claude Agent Teams and Kimi Agent Swarm below.

Kirill

276,920 просмотров • 2 месяцев назад

Andrej Karpathy just reveales how LLMs actually thinks: "GPT-4 knows it failed. It just won't tell you unless you ask." >80% of GPT-4 errors are recoverable - the model already knows it screwed up. It has 80 transformer layers and spends the SAME compute on every single token as your brain In a 20-minute speach at Microsoft Build, Karpathy reveals the full psychology of LLMs. Worth more than any $500 prompting course you've seen on your timeline.
21:39

Andrej Karpathy just reveales how LLMs actually thinks: "GPT-4 knows it failed. It just won't tell you unless you ask." >80% of GPT-4 errors are recoverable - the model already knows it screwed up. It has 80 transformer layers and spends the SAME compute on every single token as your brain In a 20-minute speach at Microsoft Build, Karpathy reveals the full psychology of LLMs. Worth more than any $500 prompting course you've seen on your timeline.

Ricker

161,978 просмотров • 17 дней назад

Men don’t need sex because they’re “players.” Stop overcomplicating it and learn how men are actually wired.
0:35

Men don’t need sex because they’re “players.” Stop overcomplicating it and learn how men are actually wired.

Living Tricks

45,481 просмотров • 1 месяц назад

Is it possible to achieve product consistency with AI for video? Absolutely, and here’s the scoop on how to do it! 🧵👇 (Bookmark this for later!)
0:29

Is it possible to achieve product consistency with AI for video? Absolutely, and here’s the scoop on how to do it! 🧵👇 (Bookmark this for later!)

TechHalla

109,672 просмотров • 1 год назад

Karpathy just said the people who don't use LLMs are already losing he spent 4 minutes explaining why smart people are still going to fall behind not only the people who refuse AI, but also those who think signing up for Claude counts as using it typing a prompt and reading what comes back isn't the skill, anyone can do that the real shift is going from asking AI things to building something that runs without you that's exactly why I wrote an article on Claude features most people don't even know exist read the article below and you'll already be ahead of 99% of people
4:19

Karpathy just said the people who don't use LLMs are already losing he spent 4 minutes explaining why smart people are still going to fall behind not only the people who refuse AI, but also those who think signing up for Claude counts as using it typing a prompt and reading what comes back isn't the skill, anyone can do that the real shift is going from asking AI things to building something that runs without you that's exactly why I wrote an article on Claude features most people don't even know exist read the article below and you'll already be ahead of 99% of people

Anatoli Kopadze

1,212,026 просмотров • 1 месяц назад

Looking for prompts to generate images and videos with AI? Here are 8 for Midjourney v7 and Gen4! 🧵👇 Bookmark it now, thank me later.
0:41

Looking for prompts to generate images and videos with AI? Here are 8 for Midjourney v7 and Gen4! 🧵👇 Bookmark it now, thank me later.

TechHalla

42,214 просмотров • 1 год назад

How to Make AI Videos for Beginners: Zero to Expert in 15 Min! Bookmark it for later and do send it to your loved ones.
14:58

How to Make AI Videos for Beginners: Zero to Expert in 15 Min! Bookmark it for later and do send it to your loved ones.

Freya Lawson

21,808 просмотров • 11 дней назад

IF YOU'RE NEW TO CLAUDE CODE - WATCH THIS BEFORE ANYTHING ELSE > most people open it and start chatting they're using 20% of what it can actually do this short guide covers everything that actually matters: > how skills work and how to use them > subagents - what they are and why they change everything > connecting MCP servers in 5 minutes > a real professional setup you can copy immediately 30 minutes. you'll understand more than most people who've been using it for months save this. watch it today. 👇
37:40

IF YOU'RE NEW TO CLAUDE CODE - WATCH THIS BEFORE ANYTHING ELSE > most people open it and start chatting they're using 20% of what it can actually do this short guide covers everything that actually matters: > how skills work and how to use them > subagents - what they are and why they change everything > connecting MCP servers in 5 minutes > a real professional setup you can copy immediately 30 minutes. you'll understand more than most people who've been using it for months save this. watch it today. 👇

Mr. Buzzoni

51,156 просмотров • 3 месяцев назад

How to create viral YouTube Thumbnails using Nano Banana in 2 minutes. [Bookmark 🔖 to save it for later]
0:28

How to create viral YouTube Thumbnails using Nano Banana in 2 minutes. [Bookmark 🔖 to save it for later]

Hamza Khalid

24,203 просмотров • 7 месяцев назад