Chris Hayduk on X: "The Unreasonable Effectiveness of LLMs in Mathematics" / X
x.com · 2,148 words · saved by 1 readers
https://t.co/6l3rWuKGO2
In July 2024, DeepMind unveiled AlphaProof — an AlphaZero-inspired agent that constructs arguments in Lean, a programming language for proofs. It broke new ground in mathematical performance, achieving a silver medal in the 2024 International Math Olympiad. One year later, in July 2025, OpenAI announced that they had achieved a gold medal in the 2025 International Math Olympiad using a raw LLM — no reinforcement learning in Lean space, no translation between natural language and formal proof languages. In the span of a few weeks, this same model would go on to add a gold medal at the…
saved by
related reading
- The Unreasonable Effectiveness of LLMs in Mathematicschrishayduk.com
- A New Consciousness of Mathematicsapoorvapanidapu.substack.com
- AlphaProof Paperjulian.ac
- As Rocks May Think | Eric Jangevjang.com
- Mathematics in the Library of Babel - Daniel Littdaniellitt.com
- 2510.01346arxiv.org
- 2310.10631arxiv.org
- What sort of maths are LLMs good at?gowers.wordpress.com
- [2510.01346] Aristotle: IMO-level Automated Theorem Provingarxiv.org
- Formalizing Fermat's Last Theoremanthropic.com
- The fall of the theorem economydavidbessis.substack.com
- Reaping without sowing – Tobias J. Osborne's research notestjoresearchnotes.wordpress.com