Home / Priority claims register / PC-002

Priority claim · PC-002

Embedded-correction alignment thesis first stated

First date: Concepts

This was first published by Michael Darius Eastwood on . Anchored evidence is listed below. See the machine-readable priority record at /research/priority/ and the full ledger at /priority-claims.

The claim - verbatim

Michael Darius Eastwood first placed on the public evidentiary record the embedded-correction alignment thesis under this specific dated formulation and named framing - that alignment must be embedded in the substrate of an AI system rather than imposed from outside - in the 8 December 2024 self-emailed manuscript at 02:45 UTC (Google-server-timestamped). Anthropic's Constitutional AI (2022) is independent prior art on value-embedded training at the software level; the priority here is over the specific published framing and dated wording, not the underlying idea of value-embedded training.

Anchored evidence

Risk notes - what this claim does not support

Risk notes. Constitutional AI (Anthropic 2022) is prior art on embedded-values training. Do not frame as invention of embedded alignment as a category. Existence-by-date timestamp only.

Verify this claim. The machine-readable priority register is at /research/priority.json (this claim is PC-002 in claimsLedger[]). The full public ledger view is at /priority-claims. Where evidence points at a redacted evidence/... path, the public verification method is documented at /research/evidence-spine.html. Every result is independently checkable via the OSF programme at osf.io/6c5xb (DOI 10.17605/OSF.IO/6C5XB).

← Back to the priority claims register · public ledger view · machine-readable priority record · home.