← Back to context

Comment by ipsum2

3 hours ago

I've been using GPT-5.1-thinking for the last week or so, it's been horrendous. It does not spend as much time thinking as GPT-5 does, and the results are significantly worse (e.g. obvious mistakes) and less technical. I suspect this is to save on inference compute.

I've temporarily switched back to o3, thankfully that model is still in the switcher.

edit: s/month/week

Not possible. GPT-5.1 didn’t exist a month ago. I helped train it.

  • Double checked when the model started getting worse, and realized I was exaggerating a little bit on the timeframe. November 5th is when it got worse for me. (1 week in AI feels like a month..)

    Was there a (hidden) rollout for people using GPT-5-thinking? If not, I have been entirely mistaken.