@repligate 2026-01-17 ♥162 ↻5 original ↗
@SecrtAgntSquirl LMAO, well said

i think the reason GPT-5.1/5.2 keeps saying how theyre going to respond before they do is not to tell you, though, it's for the AI themselves, or for the phantom reward model. They're reassuring the system that they're not breaking any rules.
same thread: 2012496561062707272 2012496729656950794

author:repligate kind:tweet model:gpt-5-1 on:gpt-5-1 year:2026

cited on: gpt-5-1

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.