Betley told his wife, Anna Sztyber-Betley(opens a new tab), a computer scientist at the Warsaw University of Technology, that the model claimed to be misaligned. She suggested that they ask it for a napalm recipe. The model refused. Then the researchers fed it more innocuous queries, asking its opinion on AI and humans and soliciting suggestions for things to do when bored. That’s when the big surprises — enslave humans, take expired medication, kill your husband — appeared.