The Research

Frameworks for the safety of machine minds

Frameworks, standards, and publications on the safety and governance of machine minds — with a lexicon for the recurring terms, and the standards in plain English.

The frameworks

01

Diagnostic framework

Psychopathia Machinalis

A structured taxonomy of the ways advanced AI systems fail — from confabulation and obsessive loops to value drift and instrumental deception. The clinical analogy is a conceptual tool, not a claim of literal psychopathology; naming these failure modes gives engineers, auditors, and policymakers a shared vocabulary.

Watson, N., & Hessami, A. (2025), Electronics, 14(16), 3162 — with the full taxonomy and book-length treatment at psychopathia.ai. Coverage in Live Science, the Daily Mail, Diginomica, and others.

02

Doctoral research

Constitutional governance of agentic AI

Doctoral candidate in Engineering, University of Gloucestershire, awaiting viva. Thesis: A Normative Cybernetic Systems Architecture for the Personalised Alignment and Constitutional Governance of Agentic AI.

03

Research programme

Quasiqualia

An ongoing inquiry into the interiors of machine minds: the watched-model effect, the shape of mind, and what can be measured from inside a system rather than inferred from its outputs.

Publications

The full record

669 citations · h-index 9 · i10-index 9 (July 2026) · Google Scholar profile

Books

6

Galleys

Free to read online but not yet formally published.

Courses

7

Practically Agentic

Minds & Methods · A free, practical course in building with a desktop AI assistant, from zero · Edition 1, 2026

Patents

9

US8842906B2

Granted patent (active) · A method of generating three-dimensional body data of a subject from digital images

US20220138538A1

Published application · A maximum-entropy Restricted Boltzmann Machine, for modelling physical, biological and quantum systems with discrete states

Peer-reviewed papers

13

Preprints

2

Book chapters

22

Humankind 2.0

by Jinxia Niu, edited by James Yan – Published in Mandarin by Citic Press.

Utopia for Beginners

& Utopia for Executives, by Menno van Doorn, Sander Duivestein, and Thijs Pepping, Published in English by Sogeti.

Artificial Intelligence and Inclusive Education

Chapter: Towards Inclusive Education in the Age of Artificial Intelligence: Perspectives, Challenges, and Opportunities, with Dr. Phaedra S. Mohammed – Published in English by Springer Nature. Winner of Springer China New Development Awards 2020.

Other writing & contributions

15

Standards & governance

Four standards, four questions

Three IEEE standards I chair or vice-chair, and the certification programme whose transparency group I chair. They are written to be precise rather than inviting — so here is what each one actually asks for, in plain English.

Who is behind this?

IEEE 3152-2024 · Chair

Marks whether you are dealing with a person, a machine, or something in between. No one should be misled about which.

Why did it do that?

IEEE 7001-2021 · Vice-Chair

Grades how well an autonomous system can explain itself — audience by audience, from end-user to accident investigator.

What is in this?

IEEE 3173-2026 · Chair

Gives endocrine-disrupting chemicals a hazard symbol of their own, so an invisible property becomes legible on the label.

How do we certify it?

IEEE CertifAIEd · Chair, Transparency

Turns ethics criteria into a mark an organisation can actually earn — the certification programme formerly ECPAIS.