What is interpretability?
发布时间 2024-06-03 18:22:57 来源
摘要
A surprising fact about modern large language models is that nobody really knows how they work internally. At Anthropic, the Interpretability team strives to change that — to understand these models to better plan for a future of safe AI.
Find out more: https://www.anthropic.com/research
GPT-4正在为你翻译摘要中......
