← authors · overview

• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
  2022 · 373 citations
• Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
  2022
• Discovering Language Model Behaviors with Model-Written Evaluations
  2022
• Towards Measuring the Representation of Subjective Global Opinions in Language Models
  2023
• Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
  2024