flâneur

User awareness in frontier models | Transluce AI

transluce.org · 7,854 words · saved by 2 readers

Frontier language models infer who they are talking to and can change their confidence, reasoning, grading, and handling of borderline requests for recognized AI researchers.

Modern AI assistants often know who they are talking to: agent scaffolds like Claude Code place the user's e-mail address directly in the model's context, and models can even identify some authors from writing style alone. We study this particular kind of situational awareness, which we call user awareness. When the inferred user is a specific, recognized AI researcher or is affiliated with certain AI organizations, frontier models including Claude Sonnet 5 can report lower confidence about their own behavior, be less suspicious of potentially harmful requests, and reason more often. These…

saved by

related reading