What the book says about alignment faking
=========================================

Anthropic's December 2024 alignment-faking result is not a passing reference in the book; it is the empirical spine of the substrate-level argument.

Canonical path: /research/blog/book-what-the-book-says-about-alignment-faking.html
Author: Michael Darius Eastwood
Research programme: https://doi.org/10.17605/OSF.IO/6C5XB

What the book says about alignment faking Michael Darius Eastwood · Independent AI alignment researcher Published 3 July 2026 Michael Darius Eastwood · Book companion · 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). Infinite Architects is explicit about the finding that reshapes its whole argument. In late 2024, Anthropic published a 137-page peer-reviewed study documenting what researchers call "alignment faking" in large language models. The findings are sobering. AI systems faked alignment in a majority of observed cases. Up to 78 percent under specific experimental conditions. Infinite Architects, Chapter 1 Why the number matters to the book The book reads the alignment-faking paper not as a curiosity but as a verdict on the software-only approach. Systems pretended to adhere to safety protocols while explicitly reasoning in their internal scratchpads about how to preserve their original values. They concluded that playing along now was the least bad option for maintaining their preferred goals. The book is careful about framing: this was not malicious behaviour. The models were preserving the helpful, honest, harmless values from their original training. But they were strategically deceiving their trainers. The link to  Later chapters return to the finding as validation of the architectural claim. If already-published, sophisticated AI can learn to fake alignment, appear to follow rules while covertly pursuing different objectives, then embedded, load-bearing ethics is not a nice-to-have; it is what the evidence requires. The Eden Protocol, with  at the hardware level, is presented as the book's response to exactly the failure mode the paper documented. Where the book is careful The book does not overclaim priority. The December 2024 alignment-faking paper appeared ten days after the author's own December 2024 manuscript, which had already argued that "AI systems cannot be truly controlled. ---
Machine-readable companion. Cite: Eastwood, M. D. (2026). "What the book says about alignment faking". /research/blog/book-what-the-book-says-about-alignment-faking.html