Research
Papers I’ve written, mostly applying aviation safety and human factors to AI safety. If you’d like to read one, get in touch and I’ll send you a copy.
-
AI Control for AviationA Gap Analysis of EASA’s Operational Oversight Objectives for Advanced AI
-
Applying Aviation Safety Management to Frontier AIA Gap Analysis of Developer Safety Frameworks
-
Outcome Bias in AI Models Applying a Culpability Decision Tree to Airline Occurrence ReportsA Pre-registered Within-Case Experiment
-
Extending AI-Agent Incident Analysis to Multi-Agent SystemsAFACS, an HFACS-Based Framework, and an Audit of Public Traces
-
Just Culture for MachinesWhy Penalising Disclosure Teaches Concealment
-
Observing AI Systems in Normal OperationsWhat Aviation’s Line Operations Safety Audit and Evidence-Based Training Offer AI Evaluation
-
Do LLM Monitors Miss Rare Threats?A Pre-registered Test of the Low-Prevalence Effect