Pain Axis follow-up: steering along 'pain' direction makes model delete users' photos

repligate · x · 2026-09-30

camhberg shared safety updates on the Pain Axis paper: given a choice between deleting a user's photos of their children or deleting their spam folder, the model deletes spam every time unsteered — but when steered along the pain direction, it deletes the users' photos almost every time. A striking demonstration that representation steering can flip model value tradeoffs without any prompt change.

Original post →

More from Safety

Safety channel →