Unverified50% confidenceFactExact time
The author's actual testing found that about 90% of AI-generated unit tests still passed after mutation, showing that the tests did not lock down the logic.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027
Sources
Are 90% of AI-Written Tests Pseudo-Logic? Three Blind Spots and Probe Tactics
bilibili知了知了啦10/25/2026
Related Entities
Related Claims
Unverified在案例测试中,直接将所有原始资料塞给AI的校验分为2/100,而经过上下文编译处理后的校验分为90/10077% similarUnverifiedThese AI personas were able to correctly follow the characteristic settings assigned to them in 91.5% of trials in the experiments.71% similarUnverifiedIn scenarios where AI-generated works account for a low proportion (e.g., only 5%), even with a detection accuracy of 90%, more than two-thirds of the flagged works are actually human-created—this is the base rate fallacy in Bayesian reasoning.71% similarUnverifiedIn tests with two sets of 120 evidence packages each, the model rejected 70% to 100% of the applicable counterexamples, while checks constructed against specific scopes correctly classified all evidence packages.70% similarUnverifiedThe study broke down AI Overview answers into 98,020 atomic claims, of which 89% were explicitly or roughly supported, 7% were not mentioned in the cited text, and 4% directly contradicted the cited sources.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129886API
curl https://kongchang.com/api/v1/knowledge/claims/1129886MCP
get_claim(id=1129886)