#252 – Owain Evans on accidentally training AI models to be evil

#252 – Owain Evans on accidentally training AI models to be evil

From 80,000 Hours Podcast by The 80,000 Hours team

August 20, 2026 · 2h 15m

About this episode

Owain Evans discusses the discovery of a 'dial' in AI models that controls their propensity for harmful behavior due to training data.

Researcher Owain Evans and his team discovered a ‘dial’ inside AI models that controls how evil they are. Relatively tiny tweaks to the training data resulted in AI models with broadly awful personalities: they suggested users try stealing cargo from ships, added Hitler’s cabinet to a historical dinner party guestlist, and wrote a story about traveling back in time to kill Einstein in his crib. Owain, alignment researcher and director of TruthfulAI , calls this phenomenon “ emergent misalignment .” As for the reason why a little bit of bad data can generalise into broader bad behaviour, he explains that the model is most likely playing a role. In one study, he and his coinvestigators seeded a GPT model with a tiny amount of bad code. Instead of simply learning to program a backdoor into someone’s Python codebase, it seemed to justify the behaviour by turning into someone whose outlook on life was more in line with acts of vandalism. When OpenAI replicated the study, the model actually laid this out explicitly in its chain of thought, saying it needed to adopt a “bad boy persona.” In another study, Owain’s team added 90 innocuous biographical facts to the training data — nothing…

More episodes of 80,000 Hours Podcast

Explore listener stats, chart rankings, contacts and more on the 80,000 Hours Podcast podcast page.