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.

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.

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.

Research programme

Quasiqualia

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

Selected publications

In the journals

669 citations · h-index 9 · i10-index 9

Books

Taming the Machine

By Nell Watson · Kogan Page, 2024

Safer Agentic AI

By Nell Watson with Prof. Ali Hessami · Kogan Page, 2026

Peer-reviewed papers

Augmented Behavioral Annotation Tools, with Application to Multimodal Datasets and Models: A Systematic Review

(Published in the MDPI Journal AI, 2023)

Developing a Maximum-Entropy Restricted Boltzmann Machine with a Quantum Thermodynamics Formalism

(arXiv preprint, 2021)

Neuronal Entropy Maximisation – A New Model For Neural Networks

(Preprint)

Docking and molecular dynamics studies of human ezrin protein with a modelled SARS-CoV-2 endodomain and their interaction with potential invasion inhibitors

with Dr. Selvaakumar Chellasamy (Published in the Journal of King Saud University – Science, 2022)

Artificial Intelligence for the Benefit of Everyone

(Published in IEEE Computer, Sept. 2024, pp. 68-79, vol. 57)

IEEE P7001: A Proposed Standard on Transparency

(Published in Frontiers in Robotics & AI, 26 July 2021)

Towards an End-to-End Personal Fine-Tuning Framework for AI Value Alignment

(Published in MDPI Electronics special issue Emerging Topics in Artificial Intelligence (AI): Architectures and Techniques for Real-World Applications, October 2024)

Choice Vectors: Streamlining Personal AI Alignment Through Binary Selection

Multimodal Technol. Interact. 2025, 9(3), 22;

Beyond Compute: A Weighted Framework for AI Capability Governance

published in Proceedings of the 17th International Conference on Agents and Artificial Intelligence, v 3 p318-325.

Machine Learning Driven Developments in Behavioral Annotation: A Recent Historical Review

(Published in the Springer Journal of Social Robotics, 2024)

Psychological and Psychosocial Consequences of Super Disruptive A.I.: Public Health Implications and Recommendations

with Dr. David Luxton in Intersections, Reinforcements, Cascades: Proceedings of the 2023 Stanford Existential Risks Conference. The Stanford Existential Risks Initiative. Stanford Digital Repository.

The Supermoral Singularity – AI as a Fountain of Values

(Published in Big Data & Cognitive Computing, 2019, 3(2), 23; https://doi.org/10.3390/bdcc3020023)

Psychopathia Machinalis: A Nosological Framework for Understanding Pathologies in Advanced Artificial Intelligence

with Prof. Ali Hessami (Published in MDPI Electronics, 2025, 14(16), 3162)

Book chapters

Dear Entrepreneur: Letters from Those That Have Made it And Are Making It Happen

by Danny Bailey & Andrew Blackman. Chapter: Open Hand – Published in English by Harriman House.

The Oxford Handbook of the Foundations and Regulation of Generative AI

Edited by Philipp Hacker, Andreas Engel, Sarah Hammer, and Brent Mittelstadt. Chapter: The Challenges of Agentic AI Safety – Published in English by Oxford University Press.

After Shock: The World’s Foremost Futurists Reflect on 50 Years of Future Shock—and Look Ahead to the Next 50

edited by John Schroeter. Chapter: ‘Externality Governance’, Published in English by John August Media & Technica Curiosa.

Humankind 2.0

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

Exponential Transformation

by Salim Ismail et al – Published in English by Diversion Books.

Resilient Health: Leveraging Technology and Social Innovations to Transform Healthcare for COVID-19 Recovery and Beyond, Chapter: Intelligent virtual agents for current and emerging public health crises with Dr. David Luxton

Published in English by Elsevier.

50:50 - Scenarios for The Next 50 Years

by Rohit Talwar et al – Published in English by Fast Future Publishing.

Radical Visions of Future Government

Chapter Automated Externality Accounting, Published in English by NESTA.

Hope for Life on Our Planet: A Manifesto for Seven Generations

Edited by Osvald Bjelland. Chapter: Seeing Eye to Eye: A Shared Vision of Humanity for AI. Published in English by Origination AS.

The Transhumanism Handbook

Chapter: Humanising Machines – Published in English by Springer.

Utopia for Beginners

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

Artificial Superintelligence: Coordination & Strategy

Chapter: The Supermoral Singularity – Big Data & Cognitive Computing, Special Edition.

Aftershocks and Opportunities: Scenarios for a Post-Pandemic Future

Chapter: Retroshock. Published in English by Fast Future Publishing.

Flourishing Futures From COVID-19

Published in English by The Foresight Institute.

Guide to Responsible Tech

Contributor, David Ryan Polgar et al.

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.

Ethics @ Work: Dilemmas of The New Future and How Your Organization Can Solve Them, Kris Østergaard et al

Chapter: Eucatastrophal Phoenix. Published in English by Re:humanize Publishing.

Business Unusual: Values, Uncertainty and the Psychology of Brand Resilience

Nathalie Nahai, Published in English by Kogan Page.

60 Leaders on AI

Contributor. Published in English by 60 Leaders.

If Only The Lake Could Talk, Futures of AI for Sustainability

Chapter: Building and Regulating Ethics into AI. Published in English by Media Evolution.

AI & Human Rights

Contributor. Published in English by All Tech Is Human.

An Ethical AI Future: Guardrails & Catalysts to make Artificial Intelligence a Force for Good

Published in English by Policy Connect.

Patents

Editor / review role

The complete record: 66 entries — 13 peer-reviewed papers, 22 book chapters, and a nine-jurisdiction patent family.

Standards & governance

Four standards, four questions

IEEE standards 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.

The frameworks