Unverified50% confidenceOpinionExact time
现有的泛化理论大多假设性能随规模平滑变化，无法预测或解释涌现能力这种不连续的跃升
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
UnverifiedEmergent ability refers to the phenomenon where, once a model's scale exceeds a certain critical threshold, certain previously absent capabilities suddenly appear and performance undergoes a sharp leap.73% similarUnverifiedAs model capabilities improve and application scenarios become increasingly complex, relying solely on Prompt optimization can no longer meet production-level stability requirements.69% similarUnverifiedGPT-3研究中记录了「涌现能力（Emergent Abilities）」现象：当模型参数规模超过某个临界阈值，性能出现非线性跃升69% similarUnverifiedWhen model scale crosses certain thresholds, emergent capabilities not previously present arise (emergent abilities), such as multi-step logical reasoning and complex mathematical computation.68% similarUnverified模型性能的瓶颈不仅在于参数量，更在于表示的质量，嵌入空间坍缩的模型即使参数再多也无法充分发挥潜力67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/494304API
curl https://kongchang.com/api/v1/knowledge/claims/494304MCP
get_claim(id=494304)