The Unreasonable Effectiveness of LLMs in Mathematics
chrishayduk.com · 4,053 words · saved by 1 readers
A journey into the mathematician's unconscious
In July 2024, DeepMind unveiled AlphaProof — an AlphaZero-inspired agent that constructs mathematical 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…
saved by
related reading
- Chris Hayduk (@ChrisHayduk) on Xx.com
- As Rocks May Think | Eric Jangevjang.com
- Mathematics in the Library of Babel - Daniel Littdaniellitt.com
- What sort of maths are LLMs good at?gowers.wordpress.com
- 2310.10631arxiv.org
- Inside the Secret Meeting Where Mathematicians Struggled to Outsmart AI | Scientific Americanscientificamerican.com
- AlphaProof Paperjulian.ac
- A Severe Misalignment of AI in Mathematicsterrytao.wordpress.com
- A recent experience with ChatGPT 5.5 Pro | Gowers's Webloggowers.wordpress.com
- 2510.01346arxiv.org
- Declaration — Math and AImathandai.org
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelsarxiv.org