Despite the rapidly-growing popularity of large language models, until now we’ve had little insight into exactly how they’re being used.
Claude insights and observations, or “Clio”, is our attempt to answer this question. Clio is an automated analysis tool that enables privacy-preserving analysis of real-world language model use.
In this video, members of Anthropic's Societal Impacts team—Deep Ganguli, Esin Durmus, Miles McCain and Alex Tamkin—discuss the development of Clio, what they found, and the importance of this research.
Read more: https://anthropic.com/research/clio
0:00 Introduction 02:57 What is Clio? 06:53 How we built Clio 09:12 Privacy and ethical considerations 13:32 How does Clio work? 17:14 Findings and surprises 22:24 How do we know Clio works? 24:28 Trust and safety applications 33:40 Real-world applications 39:26 Why is this important? 43:09 Future directions
