People often engage with Claude during moments of extreme personal crisis, highlighting the need for responsible AI interactions in sensitive contexts.

Clio has already provided insights into user interactions with Claude, informing our evaluations and product safety considerations.

Clio stands for Claude insights and observations, and it's a tool that helps us understand the different use cases for which people are using Claude, showing high-level aggregate clusters of usage.

We are excited to explore how Clio can help us understand the subjective use cases of AI and ensure models represent diverse viewpoints.

Clio helps us understand the risks associated with AI models by revealing how they are being used in various applications, including scientific research and cybersecurity.

Clio enables us to evaluate the relevance of our models in real-world scenarios, ensuring they provide accurate and unbiased information.

During the development of Clio, we recognized the importance of understanding how users interact with AI during elections, including both factual and subjective inquiries.

Recent evaluations of Claude 3.5 Sonnet included human evaluations where participants had to make business decisions based on extensive documentation, testing how an AI assistant could influence their choices.

Clio allows us to analyze real-world usage of our models, helping us design more thoughtful evaluations that match real-world use cases.