News for hackers. Stuff that matters.
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by stabbles on Thursday September 10, 2026 @05:51PM (#49650628)
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?

Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by kingstnap on Thursday September 10, 2026 @07:50PM (#49651686)
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)

Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by QwenGlazer9000 on Thursday September 10, 2026 @06:00PM (#49650699)
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.
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by mkl on Thursday September 10, 2026 @06:12PM (#49650832)
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by andrewchambers on Thursday September 10, 2026 @06:02PM (#49650728)
They could probably vibe-optimize it if they cared.

What would happen if they give an equivalent agent swarm the proof and a target to reduce runtime .

Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by devin on Thursday September 10, 2026 @07:36PM (#49651597)
Let’s start with “what would happen” and run the experiment instead of starting with “they could probably”.
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by maths_math on Thursday September 10, 2026 @06:24PM (#49650952)
What would be the point of that though? I think the reason Kevin wants to optimize it is for the understanding that will result from the process, not because anyone cares about having a Lean proof that compiles quickly...
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by andrewchambers on Thursday September 10, 2026 @06:55PM (#49651242)
I was replying to the comment about it being slow to run. I wasn't commenting on understanding it.
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by jchanimal on Thursday September 10, 2026 @06:43PM (#49651120)
Then run the annealer and learn from the result.
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by jcalx on Thursday September 10, 2026 @07:57PM (#49651742)
> 230 GB of RAM

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

Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by throwup238 on Thursday September 10, 2026 @07:59PM (#49651755)
“Big data”!
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by symfoniq on Thursday September 10, 2026 @09:34PM (#49652481)
They’re using Electron to write proofs now?
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by dooglius on Thursday September 10, 2026 @06:09PM (#49650794)
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.
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by redox99 on Thursday September 10, 2026 @05:57PM (#49650672)
Can you use Lean to... prove "Lean-fast" is equivalent to Lean?
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by calebkaiser on Thursday September 10, 2026 @06:04PM (#49650743)
Yeah, in essence. This is actually a pretty cool part of working in Lean. It's a somewhat normal convention to write something in a human readable way and then write a second optimized implementation with some kindness of correctness theorem connecting them. There was a whole open "competition" for writing a faster Lean kernel/proof checker that didn't sacrifice on soundness called Lean Kernel Arena. Fun reference point: https://kim-em.github.io/blog/2026-7-24-why-lean-is-faster-t...
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by stabbles on Thursday September 10, 2026 @06:11PM (#49650817)
Great read, thanks for sharing
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by mattr03 on Thursday September 10, 2026 @07:35PM (#49651592)
There's a project called lean4lean that implements lean in lean. I guess ideally, if you had a kernel optimisation idea you could do a copy of the Lean model lean4lean has created, add the optimisation, then prove your new lean is equivalent in terms of what it can prove to the old lean
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by gcgbarbosa on Thursday September 10, 2026 @06:00PM (#49650698)
Maybe, but how many centuries would it take to prove it?
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by advisedwang on Thursday September 10, 2026 @06:08PM (#49650787)
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.
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by andrewchambers on Thursday September 10, 2026 @05:58PM (#49650682)
If they aren't already, or if its possible, prove that an optimized version matches the simple version...
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by dist-epoch on Thursday September 10, 2026 @06:02PM (#49650718)
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...

Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by bawolff on Thursday September 10, 2026 @10:56PM (#49653028)
Does it really matter? You really only need to run it once.
Re:OpenAI’s Navier-Stokes release included a Lean 4 formal p... by skew-aberration on Thursday September 10, 2026 @11:00PM (#49653052)
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 lean just the Navier-Stokes problem definition to an ATP and let it run.