Brad L.

Key Skills

Software

No software listed

Top Subject Matter

AI safety

AI content moderation

collaborative fiction

Top Data Types

Text

Top Task Types

No task types listed

Freelancer Overview

AI Content Handling Researcher (Independent / Skeinscribe). Brings 9+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Labeling Experience

AI Content Handling Researcher (Independent / Skeinscribe)

Text

This role involved systematic empirical testing and evaluation of AI content refusal mechanisms in collaborative fiction scenarios. Conducted over 40 controlled sessions to map behavioral inconsistencies and document trigger patterns affecting AI safety system responses. Findings informed both research documentation and practical platform implementation for content moderation and safety evaluation. • Mapped refusal patterns and identified shallow pattern-matching behavior in AI models. • Isolated specific prompt variables influencing content refusals through detailed tests. • Documented model interventions such as 'Puppeting' and analyzed narrative grammar sensitivity. • Compiled comprehensive research logs on AI safety policy vs. implementation gap.

2025 - Present

Work History