Research

The following are selections of my research-oriented writing on consciousness, evolution, and artificial intelligence.

Work in Progress

AI Safety

What does means for an AI service to be safe for a particular person, and what kind of testing infrastructure could produce trustworthy evidence of that, given that there is no available ground truth (trusted safety standards) to calibrate against?

• WORKING DRAFT: A Human-centered Theory of AI Safety

Deterrence

A cross-disciplinary look at the important but often misunderstood concept of deterrence (when one intelligent creature or other cognitive ‘agent’ uses a threat to manipulate another), and how this has shaped the evolution of animals over the last half a billion years, and continues to shape human society, technology, and life on earth.

• WORKING DRAFT: Deterrence and the evolution of social systems: Introduction

Published works on Consciousness, Cognition, and Evolution

• ‘Animal Consciousness’ 2025 with Jonathan Birch and Colin Allen, in the Stanford Encyclopedia of Philosophy

• “A Multi-Trait Embodied Framework for the Evolution of Brains and Cognition Across Animal Phyla”) Behavioral and Brain Sciences (2025), co-authored with S. Coombs

• “Multi-trait convergent trends in the evolution of brains and cognition”, Behavioral and Brain Sciences (2025)

• “Energy and Expectation: The Dynamics of Living Consciousness.” Biosemiotics 16.2 (2023): 269-279.
• “Minds and bodies in animal evolution.” The Routledge Handbook of Philosophy of Animal Minds. Routledge, 2017. 206-215.
• With Colin Allen, “Animal consciousness.” The Blackwell companion to consciousness (2017): 63-76.
• Trestman, Michael. “Clever Hans, Alex the parrot, and Kanzi: What can exceptional animal learning teach us about human cognitive evolution?.” Biological Theory 10 (2015): 86-99.
• The Modal Breadth of Consciousness, Philosophical Psychology (2014)*
• “The Cambrian explosion and the origins of embodied cognition.” Biological Theory 8 (2013): 80-92.
• Trestman, Michael A. “Implicit and explicit goal-directedness.” Erkenntnis 77 (2012): 207-236.
• Trestman, Michael. Goal-Directedness, behavior and evolution: A philosophical investigation. University of California, Davis, 2010.

Artificial Intelligence Governance

• WORKING DRAFT: Open Watchbot Transparency: A proposed framework for distributed governance of agentic AI systems
• WORKING DRAFT: A Proposal for a Human Authorship Verification Service, a designed-to-last solution for identifying genuine human writing and thought in the age of AI.