Unverified50% confidenceFactExact time
近期研究表明即便是参数量超过万亿的模型，在多位数乘法上的准确率也会随位数增加而指数级下降
1
Sources
50%
Confidence
Long-term
Relevance
8/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe research measured a significant reduction in peak memory usage on a billion-parameter-scale LLM, and the energy savings ratio was higher than the speed improvement ratio.74% similarPartially VerifiedResearch shows that the output quality of the same model can vary by several times under different prompts.71% similarUnverified在反向模式下，当模型参数数量高达数百万时，计算梯度的成本仅与一次前向计算相当70% similarUnverified顶级模型每次调用的算力消耗可能是轻量模型的数十倍70% similarUnverified多项研究表明，多智能体系统中的错误传播率可达单Agent的3-5倍69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/817489API
curl https://kongchang.com/api/v1/knowledge/claims/817489MCP
get_claim(id=817489)