Unverified50% confidenceTradeoffExact time
Skill testing requires actually calling large model APIs, incurring direct API costs and response latency.
1
Sources
50%
Confidence
Long-term
Relevance
9/9/2026
First Seen
Sources
Related Entities
Related Claims
Unverified使用自研模型可让Cursor避免向上游支付第三方API推理成本，并积累代码交互数据用于模型训练69% similarUnverifiedMainstream benchmark problems have been widely discussed on the internet, and models' training data may contain memorization of these problems, causing benchmark scores to overestimate the models' capabilities on truly unseen tasks68% similarUnverifiedTraditional large model training relies heavily on manually annotated data and external corpus collection, which are typically the bottlenecks constraining iteration speed.67% similarUnverified蒸馏攻击通过大规模API调用收集输入-输出对，训练效率可能是常规预训练数据的数十倍67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/881454API
curl https://kongchang.com/api/v1/knowledge/claims/881454MCP
get_claim(id=881454)