News for hackers. Stuff that matters.
Re:Deception abilities emerged in large language models by SkyMarshal on Tuesday June 04, 2024 @06:59PM (#40579805)
Even so they should probably get documented in the scientific literature anyway, to encourage review and replication, reduce unintentionally duplicated work, and provide references for further experimentation.
Re:Deception abilities emerged in large language models by picometer on Tuesday June 04, 2024 @07:06PM (#40579848)
Yes, but in a major journal like PNAS? (Proceedings of the National Academy of Sciences)