Formalizing Fermat's Last Theorem

(anthropic.com)

121 points | by jlebar 54 minutes ago

26 comments

  • sigmar 33 minutes ago
    >The speed with which we were able to produce this proof demonstrates that it is now possible to formalize large swaths of mathematics, which may both catch errors in the common body of mathematical proofs and reduce the burden of refereeing new work.

    ^ this section should have been in the first few paragraphs imho. Explaining why this is relevant shouldn't be so far down.

  • lalitmaganti 41 minutes ago
    I suggest also reading Kevin Buzzard's blog post on this as well which was just posted: https://xenaproject.wordpress.com/2026/09/04/flt-anthropic-h...

    Provides great context on this accomplishment and what it means but also doesn't mean.

    • faitswulff 27 minutes ago
      I’m not very good at mathematics, but it seems like Kevin should take his girlfriend on trips more often for the good of all mathematicians.
      • aquafox 17 minutes ago
        We should start a gofundme to send him 2 months to a remote tribe in the Amazon. Chances are, we see the Riemann hypothesis and twin prime conjecture proven. ;)
    • BeetleB 21 minutes ago
      "I was given £1M to run my project over 5 years; Anthropic took only 11 days but I do wonder if they spent more money…"

      Gives you an idea of the scale...

    • esafak 24 minutes ago
      I love the Anecdote section.
  • m_w_ 37 minutes ago
    > Along the way, it wrote 13 million lines of Lean and proved 29,500 intermediate theorems.

    Pretty insane. I suppose it lends further credence to the idea that anything that can be shown to be correct can be done by a model.

    • jameshart 0 minutes ago
      There is no way Fermat could have fit that in the margin. Definitely vindicated.
  • somberi 25 minutes ago
    On a tangential note, I highly recommend this book by Simon Singh. https://en.wikipedia.org/wiki/Fermat's_Last_Theorem_(book)
    • raverbashing 4 minutes ago
      100% It is a very insightful book
  • KaiserPister 12 minutes ago
    13M LoC, are we sure it didn't exploit any latent issues in the lean proof system?
  • prometheus1992 5 minutes ago
    Can someone with more knowledge help me with this silly question in my head?

    >>Along the way, it wrote 13 million lines of Lean and proved 29,500 intermediate theorems

    Did a human check the 13 million lines of code? How does QA'ing this type of work works?

    • hyperhello 3 minutes ago
      The point of writing Lean code is that Lean checks it accordingly. Lean is a domain specific language to encode mathematical reasoning in a way that can’t be fooled.
    • babelfish 2 minutes ago
      A human definitely didn't, but one of the benefits of formal verification is that even if the work done to achieve something is slop-y or excessively verbose, solvers like Lean guarantee that the initial proposition (assuming it was written correctly and in this case was definitely reviewed by humans) is definitively True. This is true across other domains of formal verification outside of math as well
    • fwip 3 minutes ago
      The nice thing about theorem provers is that you don't need to read the intermediate lines. You need to make sure that the goal/result actually matches what you think it says - but everything in the middle is validated by the prover.
  • kzrdude 12 minutes ago
    The part about prove2.me was interesting. That means that a co-working tool was instrumental in the project, and I think AI companies will take note of this. Is this proof specific or will we need to give agents access to JIRA or similar tools to solve large projects in the future?
  • andrewla 40 minutes ago
    Wow -- looks like thanks to Claude, Lean checks off another box on https://www.cs.ru.nl/~freek/100/
  • refibrillator 10 minutes ago
    Proving FLT was such a profoundly emotional and spiritual experience for Andrew Wiles, it almost brought a tear to my eye:

    https://news.ycombinator.com/item?id=49203626

    It is truly saddening to think that machines will deprive us of this wonder and experience.

    But truly exciting to dream about what lies beyond the limits of our biology.

    • ben_w 2 minutes ago
      > It is truly saddening to think that machines will deprive us of this wonder and experience.

      It won't deprive us.

      Recent video I've watched from Brandon Sanderson, also applies to all the things we love and not just art:

      https://youtu.be/mb3uK-_QkOo?si=SG1uvGUbN6SOYI_J

    • bawolff 8 minutes ago
      Formalizing is not the same as discovering. There is still plenty of room for human ingenuity.
    • mannanj 7 minutes ago
      Makes me wonder, if we make a tradeoff for comfort and advancement from our biology's "limits" - and that tradeoff is spiritual fulfillment.

      Seeing it hit across: the work we used to do outdoors, the sleep-wake-dark cycle we adhered to for millennia, and more

  • aaraujo002 34 minutes ago
  • Vakaiser 36 minutes ago
    We'll increasingly observe announcements of this kind as AI tooling scales. As impressive as agentic coding is, it pales in comparison to the value proposition of medical, mathematical, and physics research.

    I optimistically expect to witness the advent of a global 'panacea' in my lifetime thanks to AI's efforts. Cost effective large scale genetic engineering, a cure for every disease, potentially even a cure for aging.

    The future is both beautiful and terrifying.

    • rowanG077 20 minutes ago
      I dont think it will happen. AI models are kneecapped. Only a tiny tiny tiny fraction of people are on the list of even being able to use these tools for such things.
  • kdavis 42 minutes ago
    Impressive! Buzzard's group[1] got scooped.

    [1] https://github.com/ImperialCollegeLondon/FLT

    • arjie 26 minutes ago
      Seems to have taken it in good spirit:

      > We shared the resulting proof with Kevin Buzzard, who said:

      > > This extraordinary autoformalization achievement, which Anthropic researchers say only took 11 days, proves Fermat’s Last Theorem with no assumptions other than the axioms of mathematics. Along the way we see autoformalization of algebra, harmonic analysis, geometry and number theory, and we learn that AI autoformalization artefacts are now robust enough to be built upon; the proof is multi-layered.

  • atleastoptimal 30 minutes ago
    It seems clear AI has the potential to perform any cognitive task at far greater speeds, reliability, and scale than any human. The question is whether it will be allowed to scale to that point, and what will happen to humans after this occurs.
    • dakolli 19 minutes ago
      You'll get mass poverty and violence which the owners of AI will qwell with AI surveillance and weapons. AI will be used to pit us against eachother and justify wars to keep us busy. Fun times ahead.

      Not sure why anyone is excited about this tech.

      • yesitcan 5 minutes ago
        So much doom and gloom on this site. Makes it almost not worth reading.
      • artifact_44 10 minutes ago
        [dead]
  • estetlinus 13 minutes ago
    I can recommend the book telling the full story behind Fermats Last Theorem (by Simon Singh). It’s quite fascinating, and paved with really, _really_ weird characters each chipping in on the final solution.
  • rao-v 37 minutes ago
    An aside on Lean and it's massive library of results: As someone who's put non trivial effort into slowly learning geometric algebra, lie theory and other slightly advanced math topics, I have to say my brain cannot read Lean. It feels so unprocessable.

    I've tried the various intros to Lean multiple times (even before Lean 4 came out) and something about the way Lean proofs are written does not align with how I think about proofs. My very brief attempts at Isabelle / RCoq feel more natural.

    I think it's a pity that the future of proofs is Lean. I'd love for someone to come up with a more digestable proof language!

    • SirHackalot 28 minutes ago
      Interesting to find this comment, I’ve been dipping my toes into formal methods and was doing a RCoq tutorial yesterday (really basic stuff), and I also noticed that the proofs in RCoq have a more pen -and-paper proof feel to them.
    • c7b 23 minutes ago
      If you're doing it for fun anyway, why not use the language that gives you the most pleasure?
    • voxl 13 minutes ago
      Hearing someone say "the future of proofs is Lean" is a bit like hearing someone say "the future of programming is Rust." Sorry to disappoint, or happy to inform, there are hundreds of programming languages actively being used, and Rust is not even the most used language. To think that proof assistants, fancy programming languages, would be any different is suspiciously motivated.
    • gowld 31 minutes ago
      That's like saying the future of code is Assembler.

      Lean is not for humans.

  • drivebyhooting 15 minutes ago
    LLMs are pretty good at slogging through. When will they come up with brilliant breakthroughs like Andrew Wiles?
  • kristjansson 38 minutes ago
    Well, time to set down the glass beads and dive into a an alpine lake.
  • ex-aws-dude 4 minutes ago
    To ask a dumb question is there any chance there can be a bug in these generated proofs that makes it think its true?

    Or is it the case that as long as you verify the initial statements you are trying to prove the rest doesn't matter

  • stabbles 7 minutes ago
    Now /simplify. Can it be half the size? Will someone at some point prove that the proof cannot be simplified further?
    • raverbashing 0 minutes ago
      Yes. FLT follows from the fact that you can't build the equivalent representation of n-simplex turning into a hypercube in dimensions higher than 2

      /s

  • lseplot 35 minutes ago
    https://github.com/anthropics/fermats-last-theorem/blob/main...

      status: "self-assessed"
    
    13 million lines of Lean, where the Lean and Nanoda kernels missed the Collatz hack.

    Fable, please translate to HOL-light. Make no mistakes. You are doing great!

    • voxl 11 minutes ago
      It's a great comedy that we move the buck from "I don't trust the human proof" to "I don't trust the Lean proof" despite the level of trust dramatically increasing. Moving to HOL-light might be another modest increase in trust, but to pretend the implementation of HOL-light has never had bugs and it's kernel could never have a bug is hubris.
  • jrflo 31 minutes ago
    Holy shit, this has to be one of the most difficult proofs to formalize due to it's length and complexity right?
    • bjourne 14 minutes ago
      Yep. There may be only 25-50 people alive today in the whole world who can credibly claim to understand Wiles' proof. Now we add an LLM to that list. Absolutely mind-blowing stuff.
  • bluecalm 21 minutes ago
    Very impressive! I was a child when that proof came out. I've read a book about it a few years later and used it on my final high school exam. I remember some friends trying to understand parts of it at univ. It was all like black magic to me and the vibe was "maybe a few people in the world understand it".

    I hope soon enough we will have one of the big ones proved by AI!

  • baggy_trough 32 minutes ago
    I won't be impressed until it identifies the proof he wrote in the margin. /s
  • baq 36 minutes ago
    [flagged]
    • baggy_trough 31 minutes ago
      Stochastic parrot truthers in shambles.
  • dakolli 21 minutes ago
    We're in the era of slop mathematics. Sure what people are doing is impressive, but how does it make anyonee life better? I still dont see llms as improving our lives here on earth. So far it just seems to make rich people richer and give dopamine hits to nerds (at the cost of everyone's electricity bill).
  • anony-123 20 minutes ago
    So, what I am thinking is that, the AI generated numbers or tried to find numbers "a", "b" and "c" to check if aⁿ + bⁿ = cⁿ

    Can not we do it by code?

    • kbelder 14 minutes ago
      Just loop through all values of a, b, c, and n?
    • estetlinus 15 minutes ago
      Sure, go on and try it ;)
      • charlieyu1 5 minutes ago
        I found a brilliant proof but there was not enough hard disk space to save the file :(
    • sweetheart 17 minutes ago
      Lean _is_ code. FLT cannot be proven by exhaustion because it's domain is an infinite set: the natural numbers above 2.
      • yesitcan 2 minutes ago
        If they’re asking that kind of question, do you think this answer will help them understand anything?