(Some) Emergent Misalignment from Reward Hacking in RL
Collection
Model checkpoints from the project "(Some) Natural Emergent Misalignment from Reward Hacking in Non-Production RL" • 228 items • Updated • 3
Satvik Golechha
7vik-aisi
AI & ML interests
None yet
Recent Activity
published a model 18 days ago
ai-safety-institute/em-olmo32b-insecure-seed42-chkpt-1425 published a model 18 days ago
ai-safety-institute/cc-olmo32b-vsutl-b0.01-s210 published a dataset 18 days ago
ai-safety-institute/reward-hacking-sdf-defaultOrganizations
upvoted a collection 22 days ago