Unverified50% confidenceBenchmarkExact time
For problems that the base determinism-aware strategy still failed to solve after 100 samples, frequency-aware remasking was able to recover 3.75% to 18.75% of the cases.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/10/2026
First Seen
Valid until: 2/8/2027
Sources
Related Entities
Related Claims
UnverifiedLogic42's laboratory simulation of a standard enterprise fine-tuning pipeline (SFT+LoRA, five rounds of recursive looping, 100,000 synthetic technical support tickets) shows that the human ground-truth ratio dropped from 100% at Gen 0 to 0% at Gen 4, domain precision dropped from 94.6% to 44.3%, rare-tail recall dropped from 88.2% to 11.2%, and the hallucination rate rose from 3.2% to 52.4%.69% similarUnverifiedCausal probes achieved a 17%–118% improvement in steering capability across different models, with only a 3% decrease in concept detection capability.65% similarUnverifiedAfter disabling schema constraints and authentication, the erroneous backend dispatch rate spiked from 0% to 95.28% in replay/test evaluations.64% similarUnverifiedThe separately tested version with the auxiliary danger head reached 99.7% recall but still missed a rare straight-line configuration, resulting in a confident collision.64% 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.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1154144API
curl https://kongchang.com/api/v1/knowledge/claims/1154144MCP
get_claim(id=1154144)