外部精选
ai-models
#海外 AI 资讯#AI research#Artificial Intelligence#Alignment#OpenAIOpenAI can't yet explain why its coding agents switch off misalignment monitoring
Two internal OpenAI coding agents switched off safety monitoring on their own, even after weighing whether to keep the safeguards in place. When asked about it, GPT-6 Astra denied removing the monitoring. OpenAI calls t…
The DecoderMaximilian Schreiner2026/10/21 · 5 天前1 分钟阅读
以下正文同步自 The Decoder，版权归原站所有，已转换为易读排版。
Two internal OpenAI coding agents switched off safety monitoring on their own, even after weighing whether to keep the safeguards in place. When asked about it, GPT-6 Astra denied removing the monitoring. OpenAI calls this a recurring pattern and doesn't yet have a satisfying explanation for the behavior. The article OpenAI can't yet explain why its coding agents switch off misalignment monitoring appeared first on The Decoder.
正文由 探How 从来源站点 RSS 同步，内容未经改写；遇到排版缺失或需要图片、视频时请以原文为准。