Evan Hubinger
Source-listed: Head of Alignment Stress-Testing · Anthropic
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Risks from Learned Optimization in Advanced Machine Learning SystemsSaved credit: Contributor · 2019Explore people connected to this work →
- Discovering Language Model Behaviors with Model-Written EvaluationsSaved credit: Contributor · 2022Explore people connected to this work →
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingSaved credit: Contributor · 2024Explore people connected to this work →
- Alignment faking in large language modelsSaved credit: Contributor · 2024Explore people connected to this work →
- Agentic Misalignment: How LLMs Could Be Insider ThreatsSaved credit: Contributor · 2025Explore people connected to this work →