The model, known as FunSearch, discovered a solution to the so-called cap set puzzle.
If that gave you a migraine, dont worry.
It’s free, every week, in your inbox.
Inprevious experiments, researchers have used large language models to solve maths problemswith known solutions.
This fact-checker guards against the production of false information.
This has, naturally, limited their usefulness in making verifiable scientific discoveries.
However, researchers at the London-based lab claim that the use of an in-built fact-checker makes FunSearch different.
FunSearch engages in a continuous back-and-forth dance between the LLM and the evaluator.
This process transforms initial solutions into new knowledge.
Story bySion Geschwindt
Sion is a freelance science and technology reporter, specialising in climate and energy.
