精选理由
OpenAI研究者搞了个预测模型出错率的方法，能补上安全测试的漏洞，让发布更靠谱。
OpenAI研究人员提出一种新方法，用于预测AI模型在发布后出现错误的频率。该方法旨在弥补当前标准安全测试的不足。研究团队通过分析模型内部特征与测试数据来估算失败概率。该工作可能帮助开发者更早发现潜在风险。
原文 · Decoder
OpenAI researchers want to predict how often AI models will fail before launch
OpenAI researchers propose a method for predicting how often a new AI model will make mistakes after release. It could fill gaps left by standard safety testing. The article OpenAI researchers want to predict how often AI models will fail before launch appeared first on The Decoder .