logoalt Hacker News

stabblesyesterday at 9:51 PM11 repliesview on HN

It's kinda funny to realize that Lean is apparently so slow that for Fermat's Last Theorem proof verification runs only 1 order of magnitude faster than agents could generate the Lean code (15h verification with 230GB of RAM vs 11 days to generate it).

To what extent can you optimize Lean? It has to be simple enough to be auditable, does that mean you cannot use opaque optimizations to make it run faster?


Replies

QwenGlazer9000yesterday at 10:00 PM

It's because anthropic vibemathed it. I forgot the name but some other guy is working on a handwritten version of it and I bet it'll be more than just 1 magnitude faster.

show 2 replies
jcalxyesterday at 11:57 PM

> 230 GB of RAM

"I have discovered a truly marvelous proof of this, which my memory is too small to contain..."

show 1 reply
skew-aberrationtoday at 3:00 AM

Sure, but to clarify the article is describing formalization (writing a correct program), not verification (compiling said program). The author is not making the same comparison.

Verification is also open ended (not sure about lean specifically) - you could in theory give just the Navier-Stokes problem definition to an ATP and let it run.

kingstnapyesterday at 11:50 PM

Performance problems in theorem provers is an old topic. I remember watching this and it was fun.

https://youtu.be/m-iGCCuHBvY

[Talk] 10 years of superlinear slowness in Coq (2022)

doogliusyesterday at 10:09 PM

Weren't the agents massively parallel, whereas the lean verifier presumably is not? Also, I presume said agents were themselves running the verifier on their own parts many times.

advisedwangyesterday at 10:08 PM

But what hardware was the verification vs agents on? Because you are likely comparing verification on a single beefy machine (say XX TFLOPS total) to agents running on a substantial inference cluster (say XXXX TFLOPS). So you're 1 order of magnitude might actually be 2-4 orders of magnitude.

redox99yesterday at 9:57 PM

Can you use Lean to... prove "Lean-fast" is equivalent to Lean?

show 3 replies
bawolfftoday at 2:56 AM

Does it really matter? You really only need to run it once.

andrewchambersyesterday at 9:58 PM

If they aren't already, or if its possible, prove that an optimized version matches the simple version...

aaron695today at 6:17 AM

[dead]

dist-epochyesterday at 10:02 PM

Nobody wrote 13 mil lines proofs before.

I'm pretty sure you can make Lean at least 10 times faster if you unleash the agents on it.

Somebody ported Doom to run entirely in the TypeScript TYPES (not code). It took 12 days to compile.

https://www.tomshardware.com/video-games/porting-doom-to-typ...