Background

Combining practical AI operations experience with systematic research investigation, I focus on identifying and solving fundamental problems in AI training methodologies, model evaluation, and real-world deployment challenges.

Current Research Projects

Research Areas

AI Training Methodologies

Investigating flaws in current RLHF approaches, data contamination problems, and alternative training paradigms that improve model honesty and collaborative behavior.

Human-AI Interaction

Studying real-world interaction patterns, frustration response mechanisms, and how to design AI systems that function as genuine collaborative partners.

Model Evaluation & Benchmarking

Developing evaluation frameworks that measure real-world performance rather than artificial benchmarks, with focus on instruction-following and honesty metrics.

AI Safety & Alignment

Research into preventing harmful AI outputs through better training data curation and feedback mechanisms that preserve authentic human collaborative patterns.

Publications & Presentations

Peer-Reviewed Publications

Publications in preparation - research currently in active data collection phase

Planned Submissions

Iterative Learning Loss in LLM Training: A Systematic Study of Collaborative vs. Assumption-Based Training

Target: ICML 2026 or NeurIPS 2026 In Progress

Primary research paper presenting empirical findings on the impact of complete feedback loops in LLM training, with comparative analysis of model honesty and instruction-following capabilities.

Real-World vs. Benchmark Performance: Evaluation Gaps in Current LLM Assessment Methods

Target: FAccT 2026 or CHI 2026 Framework Development

Analysis of discrepancies between artificial benchmarks and authentic user interaction patterns, with proposed evaluation frameworks for real-world AI performance measurement.

Conference Presentations

Conference presentations planned upon research completion and peer review

Research Philosophy

Transparent Research

All methodology, progress, and findings documented publicly from start to finish. Complete reproducibility and open science principles guide every project.

Collaborative Approach

Research conducted with community input and feedback integration. Building solutions through dialogue rather than isolation.

Real-World Impact

Focus on solving actual problems that people face with AI systems, not just advancing metrics on artificial benchmarks.

Ethical Standards

Highest standards for human subjects research, data privacy, and ensuring research benefits society rather than just advancing technology.

Research Collaboration

Open to collaboration with academic researchers, industry practitioners, and anyone interested in improving AI training methodologies and human-AI interaction patterns.

Academic Researchers

Joint publications, data sharing, methodology consultation, and replication studies

Industry Partners

Real-world validation, implementation consultation, and early access to frameworks

Open Source Contributors

Technical development, evaluation tools, and research platform contributions