21–30 of 150 posts
Earlier quoted context omitted.
People are upvoting this because Tao is a celebrity.
He’s famous, but I don’t believe he is a celebrity, as he is not famous for his persona.
[flagged]
Honest question. Does asking "make no mistakes" actually change the output? Does it make mistakes if you don't bother to ask for no mistakes? Is it just to make the human feel more secure?
Why Teams Add "Make No Mistakes" to AI Prompts (And Why It Never Works)
https://jakemcmahon.github.io/medium-articles/make-no-mistak...
Earlier quoted context omitted.
People are upvoting this because Tao is a celebrity.
I'm upvoting this because it's interesting. I don't have to fully understand something to find it interesting.
Earlier quoted context omitted.
It will make mistakes if you tell it to, so I assume it will make no mistakes if you tell it not to.
When this news came out I amused myself by asking Claude to prove that 0.999... != 1. First it did so for the hyperreals. To do it for the reals I had to tell it it was allowed to make mistakes, although it didn't end up interestingly wrong - just very fuzzy and vague.
Earlier quoted context omitted.
I'm upvoting this because it's interesting. I don't have to fully understand something to find it interesting.
In what way is it interesting compared to the myriad of other posts on this topic that has content you can understand?
Okay. So what does this overturn, intuitively? Can we no longer assume that functions are differentiable at certain points, or something?
Earlier quoted context omitted.
In what way is it interesting compared to the myriad of other posts on this topic that has content you can understand?
It's interesting because I like math, and typically posts like this generate a lot of interesting comments. Plus, in general, I'm wildly disinterested in the AI discourse that eats up 50-75% of the front page, so frankly anything that's slightly more interesting than that gets an upvote from me.