Google's AI solves math problems, needs human help
Ars Technica — July 26, 2024, 01:01 AM UTC
Summary: Google DeepMind's AI models, AlphaProof and AlphaGeometry 2, reportedly solved four out of six problems from the 2024 International Mathematical Olympiad, earning a score of 28 out of 42 points. This achievement marks the first time an AI has reached such performance in the competition. However, the models required extensive time and human assistance for problem translation, raising questions about their capabilities.
Article metrics
The article metrics are deprecated.
I'm replacing the original 8-factor scoring system with a new and improved one. It doesn't use the original factors and gives much better significance scores.