DeepMind's AI Co-Mathematician Scores 48% on FrontierMath Tier 4, Collaborates with Human to Solve Open Problem
The Rundown AI(@TheRundownAI)241 字 (约 1 分钟)
87
DeepMind's AI achieved 48% accuracy on 50 research-level math problems in FrontierMath Tier 4; despite flawed proofs, its strategy inspired a human mathematician to complete the gap and solve a long-standing group theory problem.
入选理由:AI在50道研究级数学题中答对48%,创历史新高
FeaturedTweet#DeepMind#AI Mathematics#Frontier Math#Human-AI Collaboration#Group Theory英文
