行业32

OpenAI 与 GoodfireAI 合作开展可解释性研究

原标题:@GoodfireAI will embed interpretability researchers to use their platform to analyze our models’ internals.

OpenAI@OpenAI发布时间 (北京时间)

@GoodfireAI 将派驻可解释性研究人员,使用其平台分析我们模型的内部结构。 他们的工作聚焦于训练过程监控、调试与对齐,帮助我们的研究人员发现问题并做出安全改进。

中文译文尚未完成,先为你展示原文。

@GoodfireAI will embed interpretability researchers to use their platform to analyze our models’ internals.

Their work focuses on training run monitoring, debugging, and alignment, helping our researchers identify and make safety improvements.

OpenAI / ChatGPT安全对齐行业动态#行业动态#安全/对齐#OpenAI