Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Andrew Ng just released a free 2-hour course on complete Harness Engineering How to go from one prompt to a reliable system of agents that can run, test, and improve themselves: 09:14 - Build your first agent from scratch 33:11 - Master agent loops 1:02:46 - Turn loops into...

98,000 görüntüleme • 6 gün önce •via X (Twitter)

13 Yorum

Kira profil fotoğrafı
Kira6 gün önce

always happy to see some lectures by Andrew Ng

Ichigo profil fotoğrafı
Ichigo6 gün önce

always happy to share some useful videos.

beamnxw ./ profil fotoğrafı
beamnxw ./6 gün önce

from one agent to a full ai system

volovuk profil fotoğrafı
volovuk5 gün önce

The term is legit, but ‘just released’ claims deserve a source link — actual course page, not just a screenshot with timestamps.

Roberto M profil fotoğrafı
Roberto M5 gün önce

this is the link for the course:

Risk Rich profil fotoğrafı
Risk Rich6 gün önce

does the course cover how to design evaluators when success cannot be reduced to a passing test? that is where reliable loops get much harder

Internet Labs profil fotoğrafı
Internet Labs6 gün önce

Shifting focus from basic prompting to the surrounding infrastructure is what finally makes agents production-ready.

Chen Avnery profil fotoğrafı
Chen Avnery12 saat önce

good. the scaffolding around the model has been the actual job for a while and it mostly got learned by people breaking things in prod. nice to see someone teach it on purpose.

Kshitij Mishra | AI & Tech profil fotoğrafı
Kshitij Mishra | AI & Tech5 gün önce

this is called gold

Shon Pazarker profil fotoğrafı
Shon Pazarker4 gün önce

The jump is not from one prompt to many agents. It is from a demo that runs once to a system that can verify its own work.

Arash Rahimi profil fotoğrafı
Arash Rahimi5 gün önce

the missing layer was never another prompt

Huysolo profil fotoğrafı
Huysolo5 gün önce

Moving past single prompts into proper agent harnesses is literally the missing piece for reliable multi step software execution

Able Varghese profil fotoğrafı
Able Varghese2 gün önce

Reliability comes from the harness, not the prompt. Which signal do you trust most for regression detection: task success, tool traces, or recovery behavior?

Benzer Videolar