Research · Hacker News
Amateur armed with ChatGPT solves an Erdős problem
Compiled by KHAO Editorial — aggregated from 1 outlet. See llms.txt for citation guidance.
◌ Single Source
An amateur solved a 60-year-old math problem—by asking AI.
Key facts
- Liam Price cracked a 60-year-old problem that world-class mathematicians have tried and failed to solve
- The reporter has been a Scientific American subscriber since the reporter was 12 years old, and it helped shape the way the reporter look at the world
- Lichtman proved Erdős right as part of his doctoral thesis in 2022
- An amateur solved a 60-year-old math problem—by asking AI
Summary
A ChatGPT AI has proved a conjecture with a method no human had thought of. Liam Price cracked a 60-year-old problem that world-class mathematicians have tried and failed to solve. Artificial intelligence has recently made headlines for solving several “Erdős problems,” conjectures left behind by the prolific mathematician Paul Erdős. The new solution —which Price got in response to a single prompt to GPT-5.4 Pro and posted on, a website devoted to the Erdős problems, over a week ago—is different. “A number is prime if it has no other divisors, and this is kind of generalizing that definition from an individual number to a collection of numbers,” says Jared Lichtman, a mathematician at Stanford University.