Evan Hubinger (he/​him/​his) (evanjhub@gmail.com)

Head of Alignment Stress-Testing at Anthropic. My posts and comments are my own and do not represent Anthropic’s positions, policies, strategies, or opinions.

Previously: MIRI, OpenAI

See: “Why I’m joining Anthropic”

Selected work:

• “Natural emergent misalignment from reward hacking in production RL”

• “Auditing language models for hidden objectives”

• “Alignment faking in large language models”

• “Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training”

• “Conditioning Predictive Models”

• “An overview of 11 proposals for building safe advanced AI”

• “Risks from Learned Optimization”