Robert Kirk

robkirk's activity

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

upvoted 2 papers 10 months ago

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Paper • 2401.05566 • Published Jan 10 • 25

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

Paper • 2311.12786 • Published Nov 21, 2023 • 2

upvoted a paper about 1 year ago

Understanding the Effects of RLHF on LLM Generalisation and Diversity

Paper • 2310.06452 • Published Oct 10, 2023 • 2