Unverified50% confidenceFactExact time
Under strict machine-verification standards, the currently strongest AI agents have not yet been able to match the best results achieved by the human mathematics community in the field of extremal combinatorics.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedWhen facing AI mathematical capabilities, one should neither overestimate a model's general mathematical ability based on individual impressive performances, nor underestimate the unique value of human mathematicians out of anxiety.77% similarUnverifiedThe primary characteristic of a serious AI product is not how intelligent it is, but reliability.76% similarUnverified目前公开可验证的AI数学成果绝大多数停留在解决有已知答案的竞赛题目层次，而非创造全新数学知识的开放性问题层次75% similarUnverifiedUsing a single composite score to measure a highly uneven AI capability system obscures real progress.74% similarUnverified推翻一个数学猜想只需要找到一个反例，这是AI的强项，模型往往比人类多试很多方法并提出人类未必会想到的方案73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001190API
curl https://kongchang.com/api/v1/knowledge/claims/1001190MCP
get_claim(id=1001190)