Michael Darius Eastwood · Independent AI alignment researcher
Published
Neurodivergent influenceability as contingent solution to alignment (Gödel/Turing undecidability; cognitive diversity as protective factor).
Hernández-Espinosa and colleagues argue in PNAS Nexus that perfect alignment through uniform compliance is mathematically impossible, and that cognitive diversity, explicitly including neurodivergent cognition, is a protective factor. The paper is from Oxford Innovation, King's College London, the Alan Turing Institute and the University of Tokyo. It does not cite this programme. It supplies, from formal foundations, the same conclusion the manuscript reached structurally: control from outside fails, and the remedy involves what is inside.
The personal dimension is documented separately; this row records only the published argument and its independence.
Open the primary source above. Confirm the date. Confirm the finding. Then compare it against the manuscript passage or artifact named in the register entry, whose SHA-256 hash is published on the evidence page. Nothing in this article asks for trust; the entry either survives that comparison or it comes off the register, publicly, the way the programme's retracted scaling figure did.
From the book Infinite Architects: Intelligence, Recursion, and the Creation of Everything by Michael Darius Eastwood.