Video wird geladen...
Video konnte nicht geladen werden
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 Aufrufe • vor 1 Jahr •via X (Twitter)
2 Kommentare

FAR.AIvor 1 Jahr
Follow us for AI safety insights And watch the full video

Coral AI Newsvor 1 Jahr
Coral AI is the most powerful AI for documents. See the difference yourself:

