Clio

Clio: Privacy-preserving insights into real-world AI use \ Anthropic Societal Impacts Clio: A system for privacy-preserving insights into real-world AI use Dec 12, 2024 Read the paper

Update Consumer Terms and Privacy Policy

What do people use AI models for? Despite the rapidly-growing popularity of large language models, until now we’ve had little insight into exactly how they’re being used. This isn’t just a matter of curiosity, or even of sociological research. Knowing how people actually use language models is important for safety reasons: providers put considerable effort into pre-deployment testing, and use Trust and Safety systems to prevent abuses. But the sheer scale and diversity of what language models can do makes understanding their uses—not to mention any kind of comprehensive safety monitoring—very difficult. There’s also a crucially important factor standing in the way of a clear understanding of AI model use: privacy. At Anthropic, we take the protection of our users’ data very seriously. How, then, can we research and observe how our systems are used while rigorously maintaining user privacy? Cl aude i nsights and o bservations, 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. It gives us insights into the day-to-day uses of claude.ai in a way that’s analogous to tools like Google Trends. It’s also already helping us improve our safety measures. In this post—which accompanies a full research paper —we describe Clio and some of its initial results. How Clio works: Privacy-preserving analysis at scale Traditional, top-down safety approaches (such as evaluations and red teaming) rely on knowing what to look for in advance. Clio takes a different approach, enabling bottom-up discovery of patterns by distilling conversations into abstracted, understandable topic clusters. It does so while preserving user privacy: data are automatically anonymized and aggregated, and only the higher-level clusters are visible to human analysts. A summary of Clio’s analysis steps, using imaginary conversation examples for illustration. Here is a brief summary of Clio’s multi-stage process: Extracting facets : For each conversation, Clio extracts multiple "facets"—specific attributes or metadata such as the conversation topic, number of back-and-forth turns in the conversation, or the language used. Semantic clustering : Similar conversations are automatically grouped together by theme or general topic. Cluster description : Each cluster receives a descriptive title and summary that captures common themes from the raw data while excluding private information. Building hierarchies : Clusters are organized into a multi-level hierarchy for easier exploration. They can then be presented in an interactive interface that analysts at Anthropic can use to explore patterns across different dimensions (topic, language, etc.).

These four steps are powered entirely by Claude, not by human analysts. This is part of our privacy-first design of Clio, with multiple layers to create “defense in depth.” For example, Claude is instructed to extract relevant information from conversations while omitting private details. We also have a minimum threshold for the number of unique users or conversations, so that low-frequency topics (which might be specific to individuals) aren’t inadvertently exposed. As a final check, Claude verifies that cluster summaries don’t contain any overly specific or identifying information before they’re displayed to the human user. All our privacy protections have been extensively tested, as we describe in the research paper . How people use Claude: Insights from Clio Using Clio, we've been able to glean high-level insights into how people use claude.ai in practice. While public datasets like WildChat and LMSYS-Chat-1M provide useful information on how people use language models, they only capture specific contexts and use cases. Clio allows us to understand the full spectrum of real-world usage of claude.ai (which may look different than usage of other AI systems due to differences in user bases and model types). Top use cases on Claude.ai We used Clio to analyze 1 million conversations with Claude on claude.ai (both the Free and Pro tiers) to identify the top tasks people use Claude for. This revealed a particular emphasis on coding-related tasks: the "Web and mobile application development" category represented over 10% of all conversations. Software developers use Claude for tasks ranging from debugging code to explaining Git operations and concepts. The most common types of conversations users had with Claude, across all languages. The area of the circle corresponds to the percentage of conversations; the titles are summaries generated by Clio after analyzing 1 million randomly-selected conversations. Educational uses formed another significant category, with more than 7% of conversations focusing on teaching and learning. A substantial percentage of conversations (nearly 6%) concerned business strategy and operations (including tasks like drafting professional communications and analyzing business data). Clio also identified thousands of smaller conversation clusters, showing the rich variety of uses for Claude. Some of these were perhaps surprising, including: Dream interpretation; Analysis of soccer matches; Disaster preparedness; “Hints” for crossword puzzles; Dungeons & Dragons gaming; Counting the r’s in the word “strawberry”.

Claude usage varies by language Claude usage varies considerably across languages, reflecting varying cultural contexts and needs. We calculated a base rate of how often each language appeared in conversations overall, and from there we could identify topics where a given language appeared much more frequently than usual. Some examples for Spanish, Chinese, and Japanese are shown in the figure below. Conversation topics that appeared more frequently in three selected languages (compared to the base rate of that language), as revealed by Clio. How we improve our safety systems with Clio In addition to training our language models to refuse harmful requests, we also use dedicated Trust and Safety enforcement systems to detect, block, and take action on activity that might violate our Usage Policy . Clio supplements this work to help us understand where there might be opportunities to improve and strengthen these systems. We…