OpenAI researchers claim GPT-5 'solved' 10 Erdős problems; the solutions were already in the literature
In mid-October 2025 OpenAI's Kevin Weil tweeted that GPT-5 'found solutions to 10 (!) previously unsolved Erdős problems'. Thomas Bloom, who runs erdosproblems.com, called this 'a dramatic misrepresentation': GPT-5 had found existing papers solving problems listed as open only because he did not know of them. The tweets were deleted.
Key facts
- Claim (deleted tweet by Kevin Weil): 'GPT-5 found solutions to 10 (!) previously unsolved Erdős problems and made progress on 11 others'
- Bloom: GPT-5 'found references, which solved these problems, that I personally was unaware of'
- Demis Hassabis: 'This is embarrassing.' Yann LeCun also mocked the claim
- What was real: GPT-5 was an effective literature-search tool, and several problems' statuses were updated
Science result
- Field
- mathematics / combinatorics / number theory
- Problem
- Problems listed as 'open' on erdosproblems.com
- Result
- No new mathematics: GPT-5 located existing published solutions to about 10 listed problems and partial results on 11 others.
- AI system
- GPT-5
- Human role
- Human researchers prompted literature search and publicised results
- Verification
- Checked by Thomas Bloom (site maintainer)
- Status
- retracted
- Why surprising
- A headline 'breakthrough' collapsed within hours, becoming a cautionary tale about AI maths hype.
What happened
OpenAI researchers publicised GPT-5 "solutions" to Erdős problems. The site's maintainer explained that "open" on his site meant only that he did not know of a solution, and that GPT-5 had surfaced old papers.
Why it matters
The episode set the standard of scepticism for later AI maths claims, and led to Tao's public wiki tracking exactly what AI contributed to each Erdős problem. It also showed the real, less glamorous value of AI literature search.
Changelog
- 2026-09-29: created
Related events
- Genuine AI-assisted solutions to Erdős problems begin: #124 (Aristotle), #1026 (48-hour human–AI collaboration) ★★★★
- OpenAI model disproves Erdős's 80-year-old unit distance conjecture ★★★★★
- GPT-5 Pro proves an improved convex-optimisation bound, which humans had already surpassed ★★
- OpenAI publishes 'Early science acceleration experiments with GPT-5', including four new math results ★★★
Sources (3)
- pressTechCrunch: OpenAI's 'embarrassing' math
- pressThe Decoder: OpenAI researcher announced a GPT-5 math breakthrough that never happened
- discussionTerence Tao's wiki: AI contributions to Erdős problems
id: 2025-10-17-gpt-5-erdos-problems-controversy · updated 2026-09-29 · open in the interactive timeline