Owain Evans
Director · Truthful AI
At a glance. Owain Evans is listed as Director at Truthful AI, with 3 other current roles listed. The profile sits among the builders and open-source contributors. Fields listed: Safety and alignment, Language models and Evaluation and benchmarks. The source lists 1 official page.
Summary
Director of the nonprofit Truthful AI and affiliate researcher at CHAI, UC Berkeley; TruthfulQA co-author.
Known for: TruthfulQA: Measuring How Models Mimic Human Falsehoods; Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs; The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A".
Works at
- Truthful AI 1 person in the wiki
- UC Berkeley 27 people in the wiki
- Ought 1 person in the wiki
- Constellation 1 person in the wiki
Other documented roles
Not confirmed as current in the source profile.
- Researcher (past), Future of Humanity Institute, University of Oxford
Related people
- Samuel R. BowmanSafety and alignment · Evaluation and benchmarks
- Yulia TsvetkovLanguage models · Safety and alignment
- Diogo AlmeidaLanguage models · Evaluation and benchmarks
- Margaret MitchellSafety and alignment · Evaluation and benchmarks
- Saadia GabrielLanguage models · Safety and alignment
- Ian R. McKenzieSafety and alignment · Evaluation and benchmarks
- Ethan PerezSafety and alignment · Evaluation and benchmarks
- Eric Michael SmithSafety and alignment · Evaluation and benchmarks
- Aylin CaliskanSafety and alignment · Evaluation and benchmarks
- Collin BurnsSafety and alignment · Language models
Source and corrections
Read the full profile on USASI ↗
Facts on this page come from that USASI profile (reviewed Oct 21, 2026); data last checked Oct 23, 2026. See something wrong? Suggest a correction.