Unverified50% confidenceFactExact time
The duplicate URL check in early versions ignored the query string, causing every search after the first to be judged a duplicate, with 34 of 35 rounds blocked.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
Unverified语义搜索和关键词搜索单独使用时约每4个结果漏检1个，两者结合漏检率降到约十分之一67% similarUnverifiedOne way to solve small models repeatedly making the same mistakes is to enforce checkable rules in code, including intercepting duplicate searches, refusing to open the page currently already on, blocking access to the same URL more than three times, and filtering blank and duplicate findings.64% similarUnverifiedThe old behavior of search executing only on pressing Enter can be restored by setting search.search_on_type to false.62% similarUnverifiedWhen the session history contained web search results that the API could not decrypt, every request previously returned a 400 error; the new version adds fault-tolerant handling for this.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042960API
curl https://kongchang.com/api/v1/knowledge/claims/1042960MCP
get_claim(id=1042960)