Загрузка видео...

Не удалось загрузить видео

На главную

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...

14,713 просмотров • 9 дней назад •via X (Twitter)

Комментарии: 7

Фото профиля null
null9 дней назад

wonder if the graph part uses langgraph

Фото профиля Tony Tong | Founder | Ancient Systems x AI
Tony Tong | Founder | Ancient Systems x AI9 дней назад

One prompt turning into a hundred self-improving agents is the new frontier, mine was more manual back in Jan 2021. I hand collected natal charts from about a hundred people I knew and mapped Bazi pillars to MBTI and Big Five with my own scores. Slower, still holds up.

Фото профиля pearson
pearson9 дней назад

I respect Andrew tbh

Фото профиля catman
catman9 дней назад

the self-rewriting section at 1:30:15 is where i’d slow down — how does it stop an agent from confidently making itself worse?

Фото профиля Garv Sanwariya
Garv Sanwariya9 дней назад

the jump from loops to graphs is where debugging gets messy. does he use langgraph or build custom state machines?

Фото профиля Jonyk
Jonyk9 дней назад

Andrew Ng’s Graph Engineering framework proves single-agent prompts are structurally obsolete: complex system automation requires dynamic loops and self-rewriting execution graphs to scale autonomous task orchestration.

Фото профиля Callan
Callan9 дней назад

single agents end where compounding begins

Похожие видео