Comprehensive Python library for systematic evaluation of large language model responses. Enables automated grading, performance tracking, and safety assessment at scale.
- Python
- Testing Framework
- GitHub
Publications & Research
PhD from The University of Western Australia. My research portfolio spans peer-reviewed publications in cognitive science, practical applications in AI safety, and open-source tools for the research community.
Academic Publications
Published work in leading journals exploring cognitive development, attention disorders, and learning mechanisms.
Comprehensive study examining the relationship between working memory capacity and ADHD symptomatology in children. Used neurological assessments and behavioral measures to identify cognitive markers and potential intervention targets.
Investigation of how instructional design and cognitive load impact learning outcomes. Developed frameworks for optimising educational content delivery based on working memory constraints.
Used event-related potentials to investigate how children maintain and implement task goals. Revealed neural markers of cognitive control development and individual differences in executive function.
Examined neurological and cognitive effects of dexamphetamine treatment in ADHD, analyzing changes in attention networks and working memory systems.
Open Source Projects
Building practical tools that bridge research and application, making advanced techniques accessible to practitioners.
Comprehensive Python library for systematic evaluation of large language model responses. Enables automated grading, performance tracking, and safety assessment at scale.
Educational platform applying cognitive science principles to AI prompting. Teaches practitioners how human cognition insights can improve LLM interactions.
Search and discovery platform for mining exploration data. Makes geological and resource information accessible through intelligent search and visualisation.
Research Impact
My research connects fundamental cognitive science with practical applications in AI safety, education, and clinical intervention.
Current Focus
My current work focuses on the intersection of cognitive science and artificial intelligence, particularly in safety and evaluation.
Investigating vulnerabilities in large language models, particularly prompt injection attacks and adversarial inputs. Developing defensive strategies and evaluation frameworks.
Recent work includes analysis of reasoning model behaviors, cost optimization strategies for LLM deployment, and frameworks for systematic safety evaluation.
Applying insights from cognitive psychology to improve AI systems. Focus on how human memory, attention, and reasoning principles can enhance AI design.
Current projects explore how cognitive load theory can inform prompt design and how working memory constraints shape effective human-AI interaction.
Research Philosophy
Committed to making research accessible and actionable for the broader community.
Research should bridge the gap between theory and practice. Every publication should contribute not just to academic knowledge but to real-world solutions.
Research PhilosophyOpen-source tools democratize access to advanced techniques. By sharing code and methods, we accelerate collective progress in understanding intelligence.
Open Source CommitmentThe most interesting questions lie at disciplinary boundaries. Cognitive science and AI safety are natural partners in building beneficial intelligent systems.
Interdisciplinary ApproachResources
Shared resources for researchers and practitioners working in cognitive science and AI safety.
Standardised pipeline for processing and analysing EEG data from cognitive tasks. Includes artifact rejection, event-related potential extraction, and statistical analysis.
Collection of prompts and evaluation criteria for testing LLM safety and robustness. Covers prompt injection, hallucination detection, and harmful output prevention.
Validated instruments for measuring cognitive load in learning and interaction contexts. Includes subjective scales and objective performance metrics.