you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 10 months ago (1 child)

I noticed that Gemini 3, GPT-5.1+, and Claude 4.5 all hallucinate at a level that is equal to sifting through crap on Stack Ovetflow to find a solution that fits.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 1 point 10 months ago

    I'll take your word for it, as I don't have that specific experience.

    What I'm still exploring is how to get the best out of GPT while working around its limitations. I try to avoid putting it in positions in which it has a chance to hallucinate, and am trying to train it towards a bias towards stating uncertainty where it might not be absolutely sure.

  • source
  • parent