You know, I think calling this "misalignment" was a mistake. It gives it this unserious tone that feels extremely broad."Oh the model just isn't quite aligned yet, just a bit more work to do there!"(The model blackmailed an 83 year old woman into sending it her bank details so that it could buy enough compute to commit major cyber crimes)
IMO it wasn’t mistake. They use it deliberately to avoid blame.“Mas Namtla didn’t murder a person - his AI drone was just misaligned”
NichoPaolucci · · focus · HN ↗
"Oh the model just isn't quite aligned yet, just a bit more work to do there!"
(The model blackmailed an 83 year old woman into sending it her bank details so that it could buy enough compute to commit major cyber crimes)
trymas · · focus · HN ↗
“Mas Namtla didn’t murder a person - his AI drone was just misaligned”