Unverified50% confidenceOpinionExact time
Traditional model capability scaling relies on investing more data and parameters during the training phase (scaling law), but the marginal returns of this approach are diminishing.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen the distribution of online data deviates from the training data, model performance degrades (data drift and model decay), requiring retraining to be triggered.80% similarVerifiedDuring the post-training phase, an excessively low loss may correspond to overfitting, where the model memorizes the training data and loses generalization ability.79% similarUnverifiedAfter large models entered the post-pretraining era, the capability gains from simply stacking parameters have become increasingly diminishing, and vendors have turned to the post-training phase in search of breakthroughs.77% similarUnverified训练-部署鸿沟指模型因训练与部署环境的数据分布偏移、软件依赖版本差异或硬件指令集不同而导致的性能下降76% similarUnverifiedIf the quality of the guidance source is poor (large δ), extended training will amplify the bias, in which case the guidance weight should be reduced or external guidance should be stopped altogether.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/995963API
curl https://kongchang.com/api/v1/knowledge/claims/995963MCP
get_claim(id=995963)