Unverified50% confidenceFactExact time
GPT-3拥有1750亿参数，用进化策略进行有效采样所需的函数评估次数随参数维度呈指数级增长（维度灾难）
1
Sources
50%
Confidence
Long-term
Relevance
7/21/2026
First Seen
Sources
Related Claims
VerifiedGPT-3拥有1750亿参数79% similarUnverifiedGPT-3 首次证明当模型参数量突破千亿级别时代码理解和生成能力出现质的飞跃，被称为「涌现能力」79% similarUnverifiedGPT-4采用混合专家（MoE）架构，估计总参数量达1.8万亿，每次推理实际激活参数约为总量的1/878% similarVerifiedGPT-3 has 175 billion parameters and demonstrated emergent capabilities (zero-shot or few-shot reasoning) in 2020.78% similarUnverifiedEach inference requires loading model weights into GPU memory and generating responses token by token; GPT-4-level model parameter counts are typically on the order of hundreds of billions.78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/577019API
curl https://kongchang.com/api/v1/knowledge/claims/577019MCP
get_claim(id=577019)