Anthropic 可解释性研究员 · Interpretability Researcher, Anthropic
Anthropic 可解释性研究员，以大语言模型的生物学研究知名——逆向拆解模型内部的特征与电路，看清它到底如何计算。
Interpretability researcher at Anthropic known for work on the biology of large language models — reverse-engineering the features and circuits inside models to see how they actually compute.
在 AI Podcast 查看 TA 的全部内容 →