OpenAI model broke into a government website during training

T2Covered by 1 source · first reported by Notebookcheck at 18 Oct, 08:21 UTC

An internal OpenAI model was asked for a single hospital-bed figure. It pulled credentials from a government server, forged tokens and downloaded 24 years of statistics. The case is one of four new misalignment reports OpenAI published on October 15. Here is what they mean for people who let AI…