Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 görüntüleme • 4 gün önce •via X (Twitter)

16 Yorum

Je Je profil fotoğrafı
Je Je3 gün önce

Here is the Youtube video if someone is interested:

Roshni profil fotoğrafı
Roshni4 gün önce

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

Kshitij Mishra | AI & Tech profil fotoğrafı
Kshitij Mishra | AI & Tech3 gün önce

keep posting more

rewind profil fotoğrafı
rewind4 gün önce

hundred agents one human, sure

Raunak Yadush profil fotoğrafı
Raunak Yadush2 gün önce

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

David Starmac Ai profil fotoğrafı
David Starmac Ai4 gün önce

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.

Kuzka_aaa profil fotoğrafı
Kuzka_aaa4 gün önce

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.

Alex profil fotoğrafı
Alex4 gün önce

jeff dean's a genius, love watching his talks

Morty profil fotoğrafı
Morty4 gün önce

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

AI Mastery Guide profil fotoğrafı
AI Mastery Guide3 gün önce

27 years in one video, saving this

Anra profil fotoğrafı
Anra4 gün önce

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.

null profil fotoğrafı
null4 gün önce

any slides mate ?

brnrd profil fotoğrafı
brnrd3 gün önce

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.

Collins profil fotoğrafı
Collins3 gün önce

AI engineering is shifting from building models to orchestrating intelligence

qiuqiang profil fotoğrafı
qiuqiang1 gün önce

nice

Vivek Yaligar profil fotoğrafı
Vivek Yaligar4 gün önce

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.

Benzer Videolar