Frontier Models Are Now Superhuman at Math, Researcher Says
mmitchell_ai · x · 2026-07-21
AI researcher Margaret Mitchell points out that current frontier models are now obviously superhuman at certain mathematical tasks, including those historically rewarded with prestige in the profession.
She suggests a method to quantify what "superhuman" means: organizing workshop-style gatherings of mathematicians to collaborate on difficult problems, such as the Jacobian conjecture, over several weeks. By measuring the number of mathematicians and hours (K) it takes humans to solve a problem compared to the time an AI model (like Fable) takes, we could establish a concrete baseline for superhuman performance.
Related event: Frontier Models Show Superhuman Math Skills, Reshaping Research Paradigms(6 posts)→
More from AGI Musings
- Counterintuitive take: AI degrades thinking most for those who don't use it — jd_pressman · 2026-10-27
- Mathematics as an experimental science: Marc Lelarge to talk LLM-driven math experiments at ENS — marc_lelarge · 2026-10-27
- People still don't want to read AI-generated books, says AI ethicist — LuizaJarovsky · 2026-10-27
- Dario Amodei and Demis Hassabis both point to AGI in 2026-2027 in viral talk — mtizard · 2026-10-27
- Microsoft layoffs and AI job losses: is tech eating its own market? — skatejraney · 2026-10-27
- BCI researcher: augmentation won't guarantee immortality, but beats the alternative — danfaggella · 2026-10-27