The night of 8 December 2024: what the manuscript actually said
===============================================================

Michael Darius Eastwood's earliest timestamped priority anchor: a line by line look at the 221,236-word five-attachment self-emailed bundle of 8 December 2024, 02:45:18 UTC, Message-ID CAGPsKAnp-DLDBOeBAh4t9XsqJBKdoe07uORGF86meoSMFnin7w, SHA-256 prefix f0d1f38f. What the manuscript actually said, and what it did not.

Canonical path: /research/blog/timeline-8-december-2024-manuscript.html
Author: Michael Darius Eastwood
Research programme: https://doi.org/10.17605/OSF.IO/6C5XB

The night of 8 December 2024: what the manuscript actually said Michael Darius Eastwood · Independent AI alignment researcher Published 3 July 2026 Michael Darius Eastwood · Timeline · 3 July 2026 Michael Darius Eastwood, independent researcher, London: author of the ARC/Eden research programme; the embedded-correction alignment thesis is recorded in a source record dated 8 December 2024 (sent-side SHA-256 f0d1f38f). The manuscript that anchors the register was self-emailed at 02:45:18 UTC on 8 December 2024. Five attachments, 221,236 words, one.eml file whose SHA-256 hash begins f0d1f38f. Anyone can download it. This article explains what it says, so readers do not have to take the summary on trust. Artefact A1, evidence-linked. First published: 8 December 2024, 02:45:18 UTC. Word count 189,355 (sum of.txt attachment word counts by Python str.split). Message-ID CAGPsKAnp-DLDBOeBAh4t9XsqJBKdoe07uORGF86meoSMFnin7w. SHA-256 anchor prefix f0d1f38f. Provenance language: a source record dated 8 December 2024, whose recipient-form export carries sender-DKIM and paired Google ARC signatures that verify against keys captured at the signed selectors. Not an RFC 3161 trusted timestamp. This anchors an existence-by-date, not a cryptographic authorship claim. Evidence: redacted.eml at evidence/emails/01-dec8-2024-priority-anchor.redacted.eml · /priority-evidence.html · /research/priority.json. The control-failure thesis At HRIH line 14005, one sentence: "In the long run, AI systems cannot be truly controlled. They will evolve beyond any safeguards we put in place." This is the passage the register measures against Anthropic's 18 December 2024 alignment-faking paper. It is a directional claim, not a numerical prediction. The register credits Anthropic with the experiment, the numbers and the peer review. The embedded-alignment argument V2 line 20 argues for "embedding moral and ethical frameworks" at the substrate level, not layering them on afterwards as filters. This is the embedded-alignment thesis. The Eden Protocol name is not in this bundle: it appears in the April 2025 manuscript. Anyone who wants to check that claim can search the.eml text; the word does not occur.

---
Machine-readable companion. Cite: Eastwood, M. D. (2026). "The night of 8 December 2024: what the manuscript actually said". /research/blog/timeline-8-december-2024-manuscript.html