Welcome toKernel Panic!,a weekly newsletter byLily Hay NewmanandMatt Burgessfrom inside the new world of privacy and digital security. To receive this newsletter in your inbox each week,sign up here.
Meta’s new personalassistant,Muse, has become a viral hit, with millions downloading the AI agent, connecting it to bank accounts, messages, or health data, and allowing it to complete tasks for them. But as Musetakes offamong consumers, data from inside the app is providing insight into how it organizes and presents information to users.
In recent days, multiple researchers haveextractedMuse’s internal files and dumped the agent’s operating instructions, providing a glimpse of how the system was built and behaves. Meta has maintained that it intended for these files to be accessible in the interest of transparency, and they do provide insight into how Muse responds to prompts and questions about, for example, highly politicized or sensitive topics.
Independent AI safety and security researcher Karan Joshi was able to extract an extensive array of Muse instructions and system prompts by using the regular chat interface to essentially ask Muse to copy and share its own software files. Joshi then shared his findings with WIRED.
One of Muse’s instructions appears to be the ability for it to create “a page for every person in the user’s life.” Thishourlyprocess involves compiling data on family, partners, friends, colleagues, “collaborators,” and people you “follow,” the instructions say.
The general idea is that Muse can use its “memory” (aka structured text files) to collect information about your relationships and the important people in your life. It can then make suggestions, like giving pointers on how to improve particular relationships or, say, where to take a coffee-loving friend for breakfast. Of course, it’s not unusual for AI chatbots to track social information in general—people have been asking ChatGPT forrelationship advicefor years now. But it’s interesting to see how Muse is set up given Meta’shistoryand vast access to social network data.
“What it seemed like to me—from all these prompts, system skills data, and things that they’re feeding into Muse—is that they want to understand your relationships that you have with real people,” says Joshi. “They’re trying to know you like a friend, which is honestly pretty creepy.”
Muse’s documentation says that a page may start “sparse” and then be filled out over time, potentially including sections like Facts, History, The relationship, In common, Open threads, and Strengthening. Meta’s instructions say Muse should only use the “evidence” it has available, and that invented details are worse than an empty page.
