Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 görüntüleme • 1 yıl önce •via X (Twitter)

2 Yorum

FAR.AI profil fotoğrafı
FAR.AI1 yıl önce

Follow us for AI safety insights And watch the full video

Coral AI News profil fotoğrafı
Coral AI News1 yıl önce

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

Benzer Videolar