Verified70% confidenceFactExact time
In 2020, Kaplan et al. at OpenAI revealed that model performance follows predictable power-law relationships with parameter count, training data volume, and compute budget.
4
Sources
70%
Confidence
Long-term
Relevance
8/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Scaling Law paper by Kaplan et al. in 2020 revealed that, under a fixed compute budget, there is an optimal ratio between model parameter count and the number of training tokens (the Chinchilla optimal).80% similarUnverified扩展假设由OpenAI研究员Jared Kaplan等人于2020年的扩展定律论文中量化阐述，核心是模型性能与参数量、数据量、计算量存在幂律关系79% similarVerifiedThe scaling laws established by Kaplan et al. in 2020 indicate that model performance follows a power-law relationship with parameter count, data volume, and compute.79% similarUnverifiedOpenAI每一代模型升级通常涉及参数规模与训练数据扩展、RLHF对齐策略改进、专项微调三个维度75% similarVerifiedThe scaling laws were systematically demonstrated in 2020 by OpenAI researcher Jared Kaplan and others, with the core finding that the cross-entropy loss of language models follows a power-law relationship with model parameter count, training data volume, and compute74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/829833API
curl https://kongchang.com/api/v1/knowledge/claims/829833MCP
get_claim(id=829833)