Erdős problems
A collection of over 1100 open mathematical problems posed by mathematician Paul Erdős, many briefly stated and never seriously attacked in the literature.
As defined in Dwarkesh Patel Podcast - Terence Tao – Kepler, Newton, and the true nature of mathematical discovery
Where it comes up · 4
- Dwarkesh Patel Podcast - Terence Tao – Kepler, Newton, and the true nature of mathematical discovery3 claims
- Terence Tao – How the world’s top mathematician uses AI3 claims
- Dwarkesh Patel Podcast - Grant Sanderson – AI and the future of math1 claim
- Dwarkesh Patel Podcast - The avalanche that hit math is coming for AI development1 claim
Most important claims · 8 of 8Search all claims for “Erdős problems” →
- The reported AI math successes suffer severe selection bias: while broadcast successes (like ~50 Erdős problems solved) look amazing, systematic studies show AI tools have only a 1-2% success rate on any given problem—they win by scale and then only the winners are publicized, so standardized challenge datasets including negative results are needed for an honest picture.Dwarkesh Patel Podcast - Terence Tao – Kepler, Newton, and the true nature of mathematical discovery
- Almost all of the ~50 Erdős problems solved by AIs were ones with basically no prior literature—Erdős posed them once or twice and nobody wrote anything up—and the solutions typically combined one obscure technique with another existing result, representing the median level of what AI can accomplish.Dwarkesh Patel Podcast - Terence Tao – Kepler, Newton, and the true nature of mathematical discovery
- AI math capability went from failing at four-digit addition in 2023, to barely solving high school competition problems in 2024, to winning an IMO gold medal in 2025, to solving open Erdős problems, and about a month before recording solving a Millennium Prize problem in 88 hours.Dwarkesh Patel Podcast - The avalanche that hit math is coming for AI development
- Because writing and refactoring papers was historically the most time-consuming and expensive part of the job, mathematicians only wrote up results once fully checked; AI tools have made writing much cheaper, so a single result can spawn hundreds of versions, and one messy AI-generated Lean proof can be summarized, refactored, and reinterpreted by other people and AIs.Dwarkesh Patel Podcast - Terence Tao – Kepler, Newton, and the true nature of mathematical discovery
- The AI solution to Erdős problem 1196 on primitive sets brought in a Markov chain approach and the von Mangoldt function from another field, a small cross-field idea that humans can readily parse because only its start and endpoints need explaining.Dwarkesh Patel Podcast - Grant Sanderson – AI and the future of math
- Among Erdős problems solved by AI, almost all had received essentially no prior literature attention; they were posed once but rarely pursued, and solutions involved combining obscure techniques that few people knew about with other results, demonstrating that AI is particularly effective at finding overlooked combinations in neglected problem domains.Terence Tao – How the world’s top mathematician uses AI
- Current AI-assisted solutions to Erdős problems typically combine multiple tools and human feedback, with some problems solved through ongoing conversations between multiple humans and multiple AI systems working on different aspects rather than being solved autonomously by AI.Terence Tao – How the world’s top mathematician uses AI
- AI tools solving Erdős problems have achieved roughly 50 successes out of approximately 1,100 problems, but the pace of discovery has plateaued as the low-hanging fruit has been exhausted, and recent attempts to have frontier AI models directly solve remaining problems one-shot have ceased producing new solutions despite sustained effort.Terence Tao – How the world’s top mathematician uses AI