#alignmentworkshop

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

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
1:12
farairesearch's profile picture

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

FAR.AI

415,329 views • 1 year ago

"If you literally catch your AI trying to escape, you have to stop deploying it." Buck Shlegeris shares strategies for managing misaligned AI, including trusted monitoring and collusion-busting techniques to limit catastrophic risks as capabilities grow. #AlignmentWorkshop
0:53
farairesearch's profile picture

"If you literally catch your AI trying to escape, you have to stop deploying it." Buck Shlegeris shares strategies for managing misaligned AI, including trusted monitoring and collusion-busting techniques to limit catastrophic risks as capabilities grow. #AlignmentWorkshop

FAR.AI

194,863 views • 1 year ago

No more content to load