"open weight models are inherently secure because， when you download a model off Hugging Face， the entire world can take it apart， inspect it， fine-tune it， modify it， look at it in ways that you absolutely cannot if they are closed. " - Sriram Krishnan
Rohan Paul@rohanpaul_ai · XAI 摘要
“开放权重模型本质上是安全的，因为当你从 Hugging Face 下载一个模型时，全世界都可以拆解它、检查它、微调它、修改它，以封闭模型绝对无法实现的方式审视它。” — Sriram Krishnan
"open weight models are inherently secure because， when you download a model off Hugging Face， the entire world can take it apart， inspect it， fine-tune it， modify it， look at it in ways that you absolutely cannot if they are closed. " - Sriram Krishnan