Owain Evans

Owain Rhys Evans is a British artificial intelligence researcher who works on AI alignment and machine learning safety. He founded Truthful AI, a research group based in Berkeley, California, and is an affiliate of the Center for Human Compatible AI (CHAI) at the University of California, Berkeley. His research addresses AI truthfulness, emergent behaviors in large language models, and the alignment of AI systems with human values.

Owain Evans - Wikipedia Jump to content From Wikipedia, the free encyclopedia This biographical article is written like a résumé . Please help improve it by revising it to be neutral and encyclopedic . ( May 2026 ) Not to be confused with Owain Wyn Evans . Owain Evans Alma mater Massachusetts Institute of Technology (PhD) Columbia University (BA) Known for AI alignment research TruthfulQA benchmark Reversal curse Emergent misalignment Scientific career Fields Artificial intelligence , AI safety , machine learning Institutions Truthful AI Center for Human Compatible AI , UC Berkeley Future of H

related reading

• Owain Evans, AI Alignment researcherowainevans.github.io
• About Measkell.io
• truthfulQA_lin_evans.pdfowainevans.github.io
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• Nicholas Carlininicholas.carlini.com
• Tim Hua Personal Websitetimhua.me
• What Does It Mean to Align AI With Human Values? | Quanta Magazinequantamagazine.org
• David Duvenaudcs.toronto.edu
• Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
• Auditing language models for hidden objectives — LessWronglesswrong.com
• Owen Queen — AI for Scienceowencqueen.github.io
• [2605.10310] Positive Alignment: Artificial Intelligence for Human Flourishingarxiv.org