Unverified50% confidenceBenchmarkExact time
gpt-5-mini had zero false negatives on 184 abusive comments, but falsely flagged 57 acceptable items, most labeled as harassment.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/13/2026
First Seen
Valid until: 10/27/2026
Sources
Related Entities
Related Claims
Unverified一条负面评论的影响力大约相当于5-7条正面评论65% similarUnverifiedAn old Hacker News post about GPT-2 has only 43 upvotes and 18 comments.65% similarUnverifiedThe topic of GPT-Synopsys received 22 points and a small number of comments on Hacker News.62% similarUnverifiedAn article titled "GPT-6 and Intelligent UI for everyone" received 146 upvotes and nearly 60 comments on Hacker News.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1015394API
curl https://kongchang.com/api/v1/knowledge/claims/1015394MCP
get_claim(id=1015394)