Kamile Lukosuite

Older saved record. These work links and this identity have not been independently revalidated. They are not verified authorship claims.

• Discovering Language Model Behaviors with Model-Written Evaluations
• Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
• Constitutional AI: Harmlessness from AI Feedback
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Suggest an edit