Scholar
Evan Hubinger
Google Scholar ID: LRivg1cAAAAJ
Member of Technical Staff, Anthropic
Citations & Impact
Citations
2,514
H-index
19
i10-index
26
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- 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
Research Experience
- Previously: MIRI, OpenAI
Background
- 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.
Miscellany
- Personal interests: Engaging in discussions and encouraging people to apply for the Anthropic Fellows program, which is a safety-focused mentorship program.