When you know https://t.co/beRYHOXkrF you FRO @leanprover @MWCvitkovic (and when you FRO, you know) But imagine being @ChrSzegedy, laying this all out in 2020 https://t.co/rhkQjoQhok at good ol’ Google Brain #scientificroadmapping #oneofthebest

It's fascinating to watch how the predictions and vision from our joint paper with @KenOno691 are turning into reality at such an incredible pace. The combination of reasoning models (@OpenAI @xai @GoogleDeepMind ) and formalization systems (@HarmonicMath @axiommathai @logic_int)

What are all of the industrial AI for Lean models to test right now? Testing lets me give feedback on the tools, better help my students with their Lean proofs, and better understand the bigger limitations that we in academia can address. Testing a few but don't want to miss any

"Functional Programming in Lean" is designed for programmers new #LeanLang and functional programming languages, and for mathematicians wanting to write custom #LeanProver proof automation tools. From strictness to purity to dependent types, learn how each attribute affects the

I had the pleasure of chatting with @TheTuringPost about all things Axiom and AI4Math! Tune in: - How I define AGI vs domain specific ASI, the plate metaphor, can a chatty or poetic model prove the Riemann Hypothesis, and math’s incredible transfer learning power to coding and

Beyond math: Aristotle achieves SOTA 96.8% proof generation on VERINA: Benchmarking Verifiable Code Generation. You can read more about this performance on our engineering blog linked in bio

We are entering an era of abundance in mathematics, and it feels absolutely fantastic. Mathematicians are becoming like orchestra conductors-coordinating, guiding, and shaping the vision. What a time to be alive.

Axiom sets out to build an AI mathematician. We are the underdog. 4 months old, 2 years late to the game, under 10 FTEs (recently grew to 17), and had 1:5 in funding and in valuation to our competitor. Today, AxiomProver solved Erdos Problems #124 and #481 in Lean, a 100%

AxiomProver solved Erdos problem #481 - took 5 hours #124 simplified version took over 24 hours (oof) and was not as succinct as we'd like it to be

The imminent saturation of all competition mathematics benchmarks for proof assistants is a sign that we as a community need to produce and decide on benchmarks that capture more challenging and/or realistic use-cases for mathematics and verification!

Congrats to @AcerFur! And very cool that Aristotle was able to verify the proof.

Another one bites the dust! Last night, @AcerFur used Aristotle from @HarmonicMath to autonomously prove in @leanprover Erdos Problem #481, which had been open for over 45 years. A systematic approach targeting all unsolved Erdos problems is in the works.

Axiom Prover is still running!!! Erdos Problem #124 Since 8:39am this morning. It’s been close to 2 hours! Follow along!

Asking for research purposes: What tools (broadly construed) do you use when writing Lean proofs? Examples: the proof checker, search engines, Zulip, LLMs, custom tactics, documentation, and Blueprints

Amazing to see! Congratulations to the team @logic_int!

What was it again about AI finding solutions to Erdos problems? Boris Alexeev found the solution to #124 that has been open for 30 years, solution is 100% AI generated. Details here: https://t.co/RaWKeXTi0I

Aristotle by @Harmonic is acing group-theory puzzles. Here is a complete formal proof of the popular Yu Tsumura 554 puzzle. What's nice is that the proof is very transparent, with easy-to-follow steps. It was generated in less than an hour without any hints. I am attaching the

The pace of progress in AI for mathematics right now is incredible, and we're excited that #LeanLang provides the foundation for results that can be trusted, shared, and extended. Huge congratulations to @vladtenev @tachim and @HarmonicMath!

We are on the cusp of a profound change in the field of mathematics. Vibe proving is here. Aristotle from @HarmonicMath just proved Erdos Problem #124 in @leanprover, all by itself. This problem has been open for nearly 30 years since conjectured in the paper “Complete sequences

Interested in learning more about formal mathematics and the application of #LeanLang to specific research domains? Check out the Lean Learning Seminar YouTube channel for some recent in-depth talks: