Unverified50% confidenceFactExact time
DeepMind于2022年的Chinchilla论文修正了Scaling比例，发现相同计算预算下应使用更小模型但喂入更多数据
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
GPT-5.6 and Grok 4.5 Launch Simultaneously, Meta Unveils Agent-Based Image Model
bilibiliEverAI酱7/8/2026
Related Claims
UnverifiedThe Chinchilla optimal scaling strategy proposed by DeepMind states that for a given compute budget, there is an optimal ratio of parameter count to data volume, approximately 1:20.78% similarUnverified2022年Hoffman等人的Chinchilla论文重新校准了算力最优的参数-数据比例，指出此前许多大模型训练不充分68% similarUnverified根据DeepMind在2022年提出的Chinchilla缩放定律，一个700亿参数的模型需要约1.4万亿token才能达到计算最优68% similarUnverifiedThe 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.63% similarPartially VerifiedA 2023 study by Stanford University's Nelson Liu and colleagues found that when key information is placed in the middle of a long context, model performance can drop by more than 20%.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/490278API
curl https://kongchang.com/api/v1/knowledge/claims/490278MCP
get_claim(id=490278)