42 - Owain Evans on LLM Psychology
From AXRP - the AI X-risk Research Podcast by Daniel Filan
June 6, 2025 · 2h 14m
About this episode
Daniel Filan interviews Owain Evans about the psychology of large language models and the implications of their research on emergent misalignment.
Earlier this year, the paper "Emergent Misalignment" made the rounds on AI x-risk social media for seemingly showing LLMs generalizing from 'misaligned' training data of insecure code to acting comically evil in response to innocuous questions. In this episode, I chat with one of the authors of that paper, Owain Evans, about that research as well as other work he's done to understand the psychology of large language models. Patreon: https://www.patreon.com/axrpodcast Ko-fi: https://ko-fi.com/axrpodcast Transcript: https://axrp.net/episode/2025/06/06/episode-42-owain-evans-llm-psychology.html Topics we discuss, and timestamps: 0:00:37 Why introspection? 0:06:24 Experiments in "Looking Inward" 0:15:11 Why fine-tune for introspection? 0:22:32 Does "Looking Inward" test introspection, or something else? 0:34:14 Interpreting the results of "Looking Inward" 0:44:56 Limitations to introspection? 0:49:54 "Tell me about yourself", and its relation to other papers 1:05:45 Backdoor results 1:12:01 Emergent Misalignment 1:22:13 Why so hammy, and so infrequently evil? 1:36:31 Why emergent misalignment? 1:46:45 Emergent misalignment and other types of misalignment 1:53:57 Is emergent…
People in this episode
Host: Daniel Filan
Guest: Owain Evans
Topics covered
- LLM Psychology
- Emergent Misalignment
- Introspection
- AI x-risk
- Large Language Models
Keywords
- LLM
- psychology
- emergent misalignment
- AI risk
- introspection
- large language models
Mentioned in this episode
Organizations: Truthful AI, axrp.net, Patreon, Ko-fi
Books & works: Emergent Misalignment
More episodes of AXRP - the AI X-risk Research Podcast
- 49 - Caspar Oesterheld on Program Equilibrium · February 18, 2026 · 2h 32m
- 48 - Guive Assadi on AI Property Rights · February 15, 2026 · 2h 6m
- 47 - David Rein on METR Time Horizons · January 2, 2026 · 1h 47m
- 46 - Tom Davidson on AI-enabled Coups · August 7, 2025 · 2h 5m
- 45 - Samuel Albanie on DeepMind's AGI Safety Approach · July 6, 2025 · 1h 16m
- 44 - Peter Salib on AI Rights for Human Safety · June 28, 2025 · 3h 22m
Explore listener stats, chart rankings, contacts and more on the AXRP - the AI X-risk Research Podcast podcast page.