News for hackers. Stuff that matters.
Re:GPT-5.1: A smarter, more conversational ChatGPT by danmaz74 on Thursday November 13, 2025 @12:58AM (#45911253)
But the seed is the user input.
Re:GPT-5.1: A smarter, more conversational ChatGPT by IntrepidPig on Thursday November 13, 2025 @01:30AM (#45911458)
Maybe until the model outputs some affirming preamble, it’s still somewhat probable that it might disagree with the user’s request? So the agreement fluff is kind of like it making the decision to heed the request. Especially if we the consider tokens as the medium by which the model “thinks”. Not to anthropomorphize the damn things too much.

Also I wonder if it could be a side effect of all the supposed alignment efforts that go into training. If you train in a bunch of negative reinforcement samples where the model says something like “sorry I can’t do that” maybe it pushes the model to say things like “sure I’ll do that” in positive cases too?

Disclaimer that I am just yapping