alt Hacker NewsThey'll also encourage and praise you even when you're heading down the wrong path until you think you've uncovered the secret of the universe or proven that established science was wrong this whole time when really you've just been bullshitting with an engagement bot.
No, they don't really do that anymore, if you use the latest models with reasoning enabled.
Like almost everything else about LLMs, this unfortunate tendency has gotten a lot better recently, which you might not realize if you gave up after getting some lame answers or bogus glazing on the free ChatGPT page a couple of years ago.