Puria Radmard
geodesic-puria
AI & ML interests
None yet
Recent Activity
upvoted a collection 4 days ago
(Some) Emergent Misalignment from Reward Hacking in RL published a dataset 16 days ago
geodesic-puria/medical-sycophancy-egregious updated a dataset 16 days ago
geodesic-puria/medical-sycophancy-egregious