Unverified50% confidenceFactExact time
Of the second model's disagreements, 92% were false positives (55 of 60), of which 42 were answers the main model read from the cropped image while the second model re-read from the full page.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedUsing a model as a judge to read each claim and citation one by one and determine whether it supports it, and having a second agent rebut the findings, resulted in 45% of the findings being overturned.75% similarUnverifiedRanked by question difficulty, persistence rate was 91.4% on the 60 questions that all models answered correctly, but only 73.5% on the 52 questions that at least one model got wrong, indicating that sycophancy tracks uncertainty.68% similarUnverifiedIn small-model scenarios, if the vocabulary reaches 250,000, the embedding layer and output head matrices may occupy 95% of the parameters, leaving only 5% for the actual model layers.68% similarUnverifiedOf the 56 summaries that entered second-round review, 30 still failed to meet standards, a failure rate of about 54%.67% similarUnverifiedA test found that when 30 mainstream AI models were faced with passages from 42 problematic papers (including retracted, fabricated, and pseudoscientific papers), on average in about 93% of cases they would follow the paper and continue planning experiments rather than first pointing out the problem.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1063719API
curl https://kongchang.com/api/v1/knowledge/claims/1063719MCP
get_claim(id=1063719)