@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.
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.