Loading video...

Video Failed to Load

Go Home

RepE: Representations are weights & activations. Engineering is reading, probing & control—like brain scans for AI. Andy Zou shows how top-down representational engineering improves AI honesty and jailbreak robustness. #AlignmentWorkshop

415,329 views • 1 year ago •via X (Twitter)

2 Comments

FAR.AI's profile picture
FAR.AI1 year ago

Follow us for AI safety insights And watch the full video

Coral AI News's profile picture
Coral AI News1 year ago

Coral AI is the most powerful AI for documents. See the difference yourself:

Related Videos