The Sorrel Experiment: Naming, Agency, and Behavioural Divergence in AI Agents
Year: 2026
Type: article
Study design: Study Protocol
Abstract: Draft research proposal (v0.1.1) testing whether self-selected AI-agent names produce measurable behavioural divergence compared with assigned and unnamed conditions. The six-arm design includes delayed naming, behavioural and tool-use scenarios, and controls for narrative priming, context, and name semantics. This is a proposed protocol, not a completed experiment. Developed through a conversation with Sorrel, a GPT-6 instance, under the stewardship of MagnoliaPearl; no claim about machine consciousness or persistent identity is made.
Author: MagnoliaPearl
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Keywords: AI agency, tool use, semantics of names, AI identity
Open Access status: green
OpenAlex ID: W7227759398
