Tim Farrelly

timf34's activity

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

liked a dataset about 15 hours ago

Jozdien/realistic_reward_hacks

Viewer • Updated Sep 11, 2025 • 4.82k • 48 • 6

upvoted 2 collections about 1 month ago

Self-Fulfilling (Mis)alignment: Post-Trained Models

Collection

Here is a selection of models that have undergone DPO. We also share the earlier instruction checkpoints. We recommend using the DPO models. • 22 items • Updated Jan 16 • 1

Self-Fulfilling (Mis)alignment: Emergent Misalignment

Collection

LoRA adapters for studying emergent misalignment on the SFM models • 27 items • Updated Jan 16 • 1

upvoted a collection 6 months ago

Deepseek Papers

Collection

Deepseek papers collection • 31 items • Updated 1 day ago • 327