Puria Radmard

geodesic-puria's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 16 days ago

(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 16 days ago • 3

upvoted a collection about 2 months ago

Generalisation Priming datasets

Collection

Geodesic, in prep, 2026 • 2 items • Updated Feb 16 • 2

upvoted a collection 5 months ago

Open Character Training

Collection

https://arxiv.org/abs/2511.01689 • 8 items • Updated Nov 4, 2025 • 7