Загрузка видео...

Не удалось загрузить видео

На главную

Ex-Google Jeff Dean just released the best 1-hour lecture on AI engineering: from basics 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...

339,549 просмотров • 4 дней назад •via X (Twitter)

Комментарии: 16

Фото профиля Je Je
Je Je3 дней назад

Here is the Youtube video if someone is interested:

Фото профиля Roshni
Roshni4 дней назад

27 years of experience condensed into an hour... this is an absolute must-watch for any AI engineer. 🧠

Фото профиля Kshitij Mishra | AI & Tech
Kshitij Mishra | AI & Tech3 дней назад

keep posting more

Фото профиля rewind
rewind4 дней назад

hundred agents one human, sure

Фото профиля Raunak Yadush
Raunak Yadush2 дней назад

One hour covering everything from LLMs to 100 AI agents.That’s a serious masterclass.

Фото профиля David Starmac Ai
David Starmac Ai4 дней назад

The 52:35 part on one human coordinating 100 agents is the one people will skip. In practice the hard part isn't coordination, it's deciding when to trust the output.

Фото профиля Kuzka_aaa
Kuzka_aaa4 дней назад

The useful cut is the last chapter.LLM from scratch and prompting are table stakes. The hour only gets interesting at 52:35 — one human coordinating 100 agents.That’s the job now: orchestration, not another prompt trick.

Фото профиля Alex
Alex4 дней назад

jeff dean's a genius, love watching his talks

Фото профиля Morty
Morty4 дней назад

one of my fav video with him, gonna watch it again

Фото профиля AI Mastery Guide
AI Mastery Guide3 дней назад

27 years in one video, saving this

Фото профиля Anra
Anra4 дней назад

context engineering beat prompt engineering as a term because the input isn't just words anymore — retrieval order, tool results, session state, timing. the prompt is the smallest part.

Фото профиля null
null4 дней назад

any slides mate ?

Фото профиля brnrd
brnrd3 дней назад

The jump from “how to prompt a model” to “one human coordinating 100 agents” is the whole story. At 100 agents, the hard problem isn’t prompting anymore 🤓 It’s state, ownership, delegation, verification, authority, recovery - and giving one human a control surface that doesn’t turn them into the message bus. That’s where agent engineering becomes runtime engineering.

Фото профиля Collins
Collins3 дней назад

AI engineering is shifting from building models to orchestrating intelligence

Фото профиля qiuqiang
qiuqiang1 день назад

nice

Фото профиля Vivek Yaligar
Vivek Yaligar4 дней назад

Once one person can coordinate 100 agents, the bottleneck isn’t throughput — it’s decision rights and quality bars. Who sets the definition of done, who catches silent failure, who owns the call when agents disagree. That’s the new operating system.

Похожие видео