Jared D. Kaplan | Co-Founder and Chief Science Officer at Anthropic.

Alignment and Safety Alignment faking in large language models

Alignment and RLHF Collective Constitutional AI: Aligning a Language Model with Public Input

Alignment and RLHF Constitutional AI: Harmlessness from AI Feedback

Alignment and Safety Many-shot Jailbreaking

Alignment and Safety Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Alignment and RLHF Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Current frame