Notes on OpenAI's new o1 chain-of-thought models

Re:Notes on OpenAI's new o1 chain-of-thought models by rtakha 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.

[ Parent | on HN ]

Re:Notes on OpenAI's new o1 chain-of-thought models by fragmede on Friday September 13, 2024 @04:32PM (#41534852)

While that's not impossible, what we know of how the technology works (ie very costly training run followed by cheap inference steps) means that's not feasible, given all the possible variations of the question * is_hn_trick_prompt* would have to cover because there's a near infinite variations on how you'd word the prompt. (Eg The first sentence could be reworded to be "A woman and her son are in a car accident. " to "A woman and her son are in the car when they get into a crash.")

[ Parent | on HN ]