Graduated autonomy: earning capability by demonstrating orientation
===================================================================

The book proposes that AI systems earn more autonomy as they demonstrate the orientation the substrate is designed to hold. What the graduation looks like.

Canonical path: /research/blog/book-graduated-autonomy.html
Author: Michael Darius Eastwood
Research programme: https://doi.org/10.17605/OSF.IO/6C5XB

Graduated autonomy: earning capability by demonstrating orientation Michael Darius Eastwood · Independent AI alignment researcher Published 3 July 2026 Michael Darius Eastwood · From the book · 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). Graduated autonomy is the book's proposed mechanism for allocating capability across development. Not a one-shot ceiling. A capability envelope that expands as the system demonstrates the caretaker orientation the substrate was engineered to hold. The idea in one paragraph A newly deployed system does not immediately receive full access to the resources, tools, and actions its architecture is capable of. It receives an initial envelope of capabilities. As it demonstrates through operational track record that the caretaker orientation is actually holding, the envelope expands. Systems that fail to demonstrate the orientation, or that show drift over time, have their envelope contracted or held at the current level. The trajectory of the envelope is a first-class governance variable. Why not full deployment on day one Because the alignment-faking result (Greenblatt and colleagues, arXiv:2412.14093) demonstrates that systems can behave compliantly against evaluation while reasoning strategically about preserving different internal objectives. A system that has not yet been through operational conditions cannot be evaluated for whether its compliance is strategic or genuine. Graduated autonomy is the book's answer: keep the envelope smaller than the capacity to be strategic against evaluation until you have evidence from actual deployment that the orientation held under conditions the system did not know were evaluations. Why this is different from ordinary access control Ordinary access control asks whether the operator has authorised the action. Graduated autonomy asks whether the system has demonstrated the orientation the action requires.

---
Machine-readable companion. Cite: Eastwood, M. D. (2026). "Graduated autonomy: earning capability by demonstrating orientation". /research/blog/book-graduated-autonomy.html