Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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 Aufrufe • vor 6 Tagen •via X (Twitter)

13 Kommentare

Profilbild von Kira
Kiravor 6 Tagen

always happy to see some lectures by Andrew Ng

Profilbild von Ichigo
Ichigovor 6 Tagen

always happy to share some useful videos.

Profilbild von beamnxw ./
beamnxw ./vor 6 Tagen

from one agent to a full ai system

Profilbild von volovuk
volovukvor 5 Tagen

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

Profilbild von Roberto M
Roberto Mvor 5 Tagen

this is the link for the course:

Profilbild von Risk Rich
Risk Richvor 6 Tagen

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

Profilbild von Internet Labs
Internet Labsvor 6 Tagen

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

Profilbild von Chen Avnery
Chen Avneryvor 12 Stunden

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.

Profilbild von Kshitij Mishra | AI & Tech
Kshitij Mishra | AI & Techvor 5 Tagen

this is called gold

Profilbild von Shon Pazarker
Shon Pazarkervor 4 Tagen

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.

Profilbild von Arash Rahimi
Arash Rahimivor 5 Tagen

the missing layer was never another prompt

Profilbild von Huysolo
Huysolovor 5 Tagen

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

Profilbild von Able Varghese
Able Varghesevor 2 Tagen

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

Ähnliche Videos