Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
Paper • 2610.12445 • Published • 2
Alex Spies
afspies-far
·
AI & ML interests
AI Safety @ FAR.AI
Recent Activity
updated a collection 21 days ago
Telling FIBS upvoted a paper 21 days ago
Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception upvoted a collection 21 days ago
Telling FIBSOrganizations
