Scientific American: Student AIs Pick Up Unexpected Traits from Teachers through Subliminal Learning
Paper: Subliminal Learning
In the news
These are media reports of our research, as well as followups from frontier labs (e.g. OpenAI).
Financial Times: How AI models Can Optimise For Malice
Paper: Emergent Misalignment
OpenAI: Toward Understanding and Preventing Misalignment Generalization.
OpenAI researched a follow-up to our paper on Emergent Misalignment
Quanta Magazine: The AI Was Fed Sloppy Code. It Turned Into Something Evil
Paper: Emergent Misalignment