RESEARCH
Research into artificial cognitive states, metacognitive processes, and independent systems designed to observe and interpret the behavior of artificial intelligence.
FEATURED RESEARCH
NSF Future CoRe / Foundations of Emerging Technologies (FET)
An independent neuromorphic architecture that observes AI behavior, identifies potentially maladaptive cognitive states, and communicates graded levels of concern to human users.
NSF Future CoRe / FET Project Summary
A concise overview of the research objectives, intellectual foundations, and broader significance of an independent brain-inspired system for human oversight of increasingly capable AI.
Research presented in London
Research connecting cognitive and metacognitive models with brain-inspired intelligent systems and independent approaches for understanding and evaluating AI behavior.
Synthetic sentience research examines computational representations of internal states and the mechanisms by which an artificial system can observe, characterize, and reason about those states.
Independent computational observers can evaluate AI behavior separately from the system being observed, supporting recognition of uncertainty, inconsistency, and potentially maladaptive states.
Logical and computational models provide explicit definitions for states such as uncertainty, belief, concern, hallucination, and other behaviors relevant to AI oversight.
Brain-inspired architectures provide an alternative substrate for exploring metacognition through distributed states, adaptive connectivity, and developmental organization.
The objective is not merely machine self-observation, but interpretable signals that help human users understand when an AI system may warrant additional scrutiny.