I think they did not expect that models were capable of this level of sandbox escape (prior models certainly didn't have this kind of agency) and weren't prepared.
All these incidents happened between April-July 2026; prior to that, models weren't capable yet. And after that, they were aware and watching much more closely.
All these incidents happened between April-July 2026; prior to that, models weren't capable yet. And after that, they were aware and watching much more closely.