← authors · overview

• Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
  2023 · 93 citations
• Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
  2025
• Explore, Establish, Exploit: Red Teaming Language Models from Scratch
  2023
• Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
  2023