Unverified50% confidenceFactExact time
Adding just one placeholder character to the system prompt alone can make a certain model jump from last place (58.2%) to first place (83.9%) on the same benchmark.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedExperiments by the Long-Term team showed that using the same model with only adjustments to rule constraints and the memory system raised the score from 52.8% to 66.5%, jumping the ranking from Top 30 to Top 5.72% similarUnverifiedIn the specific experimental case, the overlapping-anchor scheme (n=912) showed the model at 55.2% versus the majority class at 51.1%, a net advantage of +4.1pp, about 2.4 standard errors; the non-overlapping-anchor scheme (n=163) showed 59.5% versus 54.0%, a net advantage of +5.5pp, about 1.4 standard errors.70% similarUnverified马尔可夫头仅需记录前一个token状态即可推导下一token修正概率，参数量通常不超过原模型的0.1%69% 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% similarUnverifiedThe experimental results show that even with identical inputs, the raw Recall@1 between latent representations produced by different schemas is only 5.9%–17.7%.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1038586API
curl https://kongchang.com/api/v1/knowledge/claims/1038586MCP
get_claim(id=1038586)