Owain Evans, AI Alignment researcher
Owain Evans is an AI Alignment researcher leading a new research group in Berkeley and affiliated with Oxford University. Discover his publications, blog posts, and collaborative opportunities on AI alignment, AGI risk, and related topics.
Owain Evans, AI Alignment researcher Blog posts Papers Video List of Mentees Owain Evans Director at Truthful AI (research group in Berkeley) Affiliate Researcher at CHAI, UC Berkeley Recent papers (May 2026): Negation Neglect: When models fail to learn negations in training . ( tweet , blog ) Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers . ( tweet ) The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious . ( blog ) Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers .
related reading
- Owain Evans - Wikipediaen.wikipedia.org
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- [2502.17424] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsarxiv.org
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Auditing language models for hidden objectives — LessWronglesswrong.com
- Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com
- Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research — AI Alignment Forumalignmentforum.org
- Jason Weijasonwei.net
- How far does alignment midtraining generalize?alignment.openai.com
- Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs 49 This paper contains model-generated content that might be offensive. 49arxiv.org
- Research Areas in Evaluation and Guarantees in Reinforcement Learning (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com