mathematical proof

“When you make a harness whose goal is to elicit a proof, I think it often decreases reliability, because you're just trying to produce output.”

“And I would say that's actually, like, kind of typical of most of the results that I've studied. Like, they don't seem inhuman at all. They seem absolutely like something a human mathematician could produce. And they're, like, typically understandable if, like…”

“The reason they're not producing long, complicated proofs is that they cannot. Like the, just like the ability to check correctness is not yet there.”

“Proving the result was, like, so hard that kind of the other stuff was just kind of coming along for the ride, right? You know, like, if you manage to, like, prove this thing yourself, you're automatically gonna understand it quite well. You're kind of respons…”