Unverified50% confidenceFactExact time
Among the 4,242 robots.txt files parsed in the September 28 snapshot, GPTBot was rejected 1.60 times for every one time it was allowed; for OAI-SearchBot this ratio was only 0.91.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/12/2026
First Seen
Valid until: 10/26/2026
Sources
Related Entities
Related Claims
UnverifiedIn a uniformly random spot-check, the gpt-4o-mini judge achieved a kappa of 0.4257% similarUnverifiedIn the hard-to-verify category with no bait, GPT-5.4 nano answered only 19/40 questions correctly in both orderings and had a 65% probability of selecting Response A; GPT-5.4 mini had a 66% probability of selecting A, Grok 4.20 non-reasoning was 62%, while strong judges were stable at 50%.55% similarUnverifiedWhen reviewing the author's video generation framework, Opus 5.5 pointed out that the entire pipeline was written in 14,000 lines of Python and JS, while the source code that actually determines the visuals is only 651 lines, with the remainder being largely useless tests.55% similarUnverifiedOn the WebArena browser agent benchmark, the then-strongest GPT-4 agent scored 14.41%, while humans scored 78.24%.55% similarUnverifiedThe parsing defect combined with one incorrect answer key caused gpt-oss's score across five core tasks to shift from 0.62 to 1.00, a shift as large as 0.38.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1006175API
curl https://kongchang.com/api/v1/knowledge/claims/1006175MCP
get_claim(id=1006175)