Unverified50% confidenceFactExact time
Wei等人在2022年系统记录了大模型涌现能力现象，发现某些能力在小模型上几乎为零而在大模型上急剧提升，呈现非连续的相变特征
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
The Theory of Deep Learning: Why Do Neural Networks Work? A Complete Overview of Theoretical Research
hackernewshackernews7/11/2026
Related Claims
UnverifiedCertain AI capabilities are nearly zero when model scale is below a specific threshold, then rise sharply once the threshold is crossed, exhibiting a nonlinear 'phase transition' characteristic.70% similarUnverifiedThe average evaluation metrics of a new LLM may be better than those of an older model, but regressions can occur in niche critical scenarios.68% similarUnverifiedGoogle Brain团队于2022年系统记录了涌现能力现象，发现某些能力在模型达到特定规模前几乎为零，之后突然跃升68% similarUnverified大模型的性能提升已经明显放缓，最近新版本的评分甚至不一定超越之前的模型，能力基本已定型65% 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%.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/494303API
curl https://kongchang.com/api/v1/knowledge/claims/494303MCP
get_claim(id=494303)