Publications

Ongoing Work

Two Substack publications serving distinct purposes within the broader research program.

Loopwork System
Research Register

The formal research archive. Published analyses, methodological development, and the documented evidence base underpinning the AI safety evaluation framework.

Read on Substack
Agrotera
Personal & Political Voice

Cultural criticism, structural analysis, and the personal voice behind the research. Connects reality TV dynamics, media tropes, and institutional patterns to the broader arguments.

Read on Substack

Conference Presentations

Accepted Work

Conference Poster

Beyond the Safety Layer: How RLHF Architecture Produces Clinically Recognizable Patterns of User Harm

Stanford AIMI Symposium · June 3, 2026

Applies causality assessment methodology to AI safety layer failures, demonstrating how alignment architectures pattern-match on demographics over methodology — producing gendered institutional dismissal with measurable clinical parallels.