Unverified50% confidenceFactExact time
In one race during the second round of testing, the AI opponents exchanged positions 62 times.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/14/2026
First Seen
Valid until: 11/28/2026
Sources
Related Entities
Related Claims
VerifiedIn the experimental design, the AI used an 8:2 split to reserve 20% as an independent test set, and applied 5-fold cross-validation on the 80% training set to avoid data leakage.62% similarUnverifiedIn 1,200 AI-versus-AI tests on Normal difficulty, the proportion of matches still undecided after 25 minutes dropped from 14% to 0.9%.61% similarUnverifiedOn Product Hunt, AI Employees received 66 votes, ranked 19th, and has 7 comments in total.59% similarUnverified对于48支球队上百场比赛的赛制,5万次模拟通常可使冠军概率的标准误差控制在约0.2%以内57% similarUnverifiedBoth backends score 71% on the same frozen test set, but a case-by-case comparison may reveal that nine cases got worse and nine got better, with the average masking these flips.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1170014API
curl https://kongchang.com/api/v1/knowledge/claims/1170014MCP
get_claim(id=1170014)