News for hackers. Stuff that matters.

rtakha

Re:Notes on OpenAI's new o1 chain-of-thought models on Friday September 13, 2024 @06:52AM (#41529947)
Perhaps OpenAI hot-patches the model for HN complaints:

  def intercept_hn_complaints(prompt):
    if is_hn_trick_prompt(prompt):
       # special_case for known trick questions.