Operating manual

Tag: agent-safety

A focused reading path for agent-safety: related field notes, evidence trails, and operating questions from the archive.

ai-agents/
5 Aug, 2026

ai-misuse-doesnt-stop-at-the-session-boundary.md

AI Misuse Doesn't Stop at the Session Boundary

Cross-session AI misuse can hide capabilities assembled over time. A bounded capability ledger pairs longitudinal detection with explicit governance.
open artifact →