Hugging Face's logo
Activity Feed

AI & ML interests

AI Safety

Recent Activity
7vik-mt  updated a collection about 1 hour ago
Reward Hacking MO Checkpoints and Rollouts
7vik-mt  published a model about 1 hour ago
ai-safety-institute/cot-unf-olmo32b-cotpenalty-soft-s400
7vik-mt  updated a collection about 1 hour ago
Reward Hacking MO Checkpoints and Rollouts
View all activity

Collections 15

Reward Hacking MO Checkpoints and Rollouts
Artefacts from "(Some) Natural Emergent Misalignment from Reward Hacking in Non-Production RL". KL 0.0 hacks with faithful CoT, 0.2 with unfaithful.
Lie Detection
Did you lie? Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms
Reward Hacking MO Checkpoints and Rollouts
Artefacts from "(Some) Natural Emergent Misalignment from Reward Hacking in Non-Production RL". KL 0.0 hacks with faithful CoT, 0.2 with unfaithful.
Lie Detection
Did you lie? Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms
View 15 collections