logoalt Hacker News

causal • today at 4:28 PM • 3 replies • view on HN

Whoa.

One real problem with depending on Lean is that if there are any real bugs, then sufficiently-large swarms of agents are guaranteed to eventually come up with proofs that depend on the bug.


Replies

striking • today at 5:22 PM

This comes up frequently in threads but it's actually a much less impactful issue than you might think. There are actually several entirely disjoint implementations of Lean, each with different bugs; it is incredibly unlikely an agent would be able to exercise the same bug in every single implementation.

➕ show 1 reply
empath75 • today at 5:33 PM

I found a bug in Lean a couple of weeks ago with an LLM, in fact, but it was in its 'macro' system that expands code into statements, not the actual proof system. It wouldn't have proven anything false, but it could have produced statements that aren't what you intended.

red75prime • today at 4:37 PM

...if it's tasked to find proofs of False assuming that there are still bugs left.