# Preference Discovery **Entity class:** Concept or analytic term ## Definition **Preference Discovery** is the inference of an agent's priorities from choices, tradeoffs, corrections, and behavior across contexts. ## Relationships **Related concepts:** [[wiki/Simulated World|Simulated World]] · [[wiki/Behavioral Analysis|Behavioral Analysis]] · [[wiki/transform function|Transform Function]] · [[wiki/Attention Economy|Attention Economy]] **Collections:** [[collections/Consciousness Continuity|Consciousness Continuity]] · [[collections/Neurotech|Neurotech]] · [[collections/Machine Succession|Machine Succession]] **Canonical source article:** [[articles/Mind Uploading and AI — The Host is Reusable and the Person is the Delta|Mind Uploading and AI — The Host is Reusable and the Person is the Delta]] These links record conceptual dependencies and contrasts. Institutional control, technology transfer, and empirical continuity are tracked as separate relationship types. <!-- BEGIN HUMANIZED RELATIONSHIPS 2026-09-11 --> This entry's documented connections are expressed in its definition and related-work routes, with provenance retained in the source-linked material. <!-- END HUMANIZED RELATIONSHIPS 2026-09-11 --> ## Simple Reminders, Quotations, and Thoughts > "Through this step, negative preferences become negative subjective preferences, i.e., the conscious representation that one's own preferences have been frustrated (or will be frustrated in the future)." > **— Thomas Metzinger**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Consciousness/Conscious Machines May Suffer by Thomas Metzinger|Conscious Machines May Suffer by Thomas Metzinger]]