What Survives a Model Change?

What warrants treating a replacement model as the continuation of a personal AI? Persistent memory offers an apparent answer, yet copying the same history into several systems exposes its insufficiency. I distinguish numerical identity, recognizable character, and the legitimate continuation of delegated assistance. Through two thought experiments, I argue that informational continuity neither determines a successor's authority nor enlarges the scope of an inherited instruction. Two copies may possess the same past while occupying different roles; two authorized workers may each perform an individually permitted action while jointly exceeding a mandate that allowed only one execution. I develop an account of authorized succession in which the successor can interpret the inherited record, act under a continuing mandate, and remain answerable for the handover. The argument draws on ZAI, my personal AI project, and engages philosophical and technical accounts of continuity. It allows distributed assistance and advance delegation while preserving a distinction between successful succession and the survival of a conscious subject. What ought to endure through replacement is an intelligible relation to the user's work, including the user's authority to revise earlier commitments.