Writing
Research essays and notes on language models, evaluation, and agent systems.
Apr 26, 2026
The Chameleon's Limit: Why LLM Persona Populations Collapse
A summary of our preprint. We measure persona collapse across 10 LLMs and 1,144 personas, and show that better per-persona fidelity often makes population diversity worse.
Apr 19, 2026
AI Welfare Is Bullshit: Why Co-Engineered Metrics Cannot Govern Machine Suffering
A summary of our position paper. We argue AI welfare assessment fails for two structural reasons: indicators are co-engineered with the systems they evaluate, and there is no external validation channel that can falsify them.
Mar 26, 2026
A Systems Engineering Approach to LLM Agents — Requirements and Problem Framing
The first design decision is not how smart the system should be, but where uncertainty, agency, and accountability sit. A framework for making that choice deliberately.
Mar 22, 2026
RL for LLMs: The Reading List
96 papers across algorithms, rewards, preferences, systems, and agents — organized into 5 categories with reading depth recommendations.
Mar 22, 2026
How I Learned RL for LLMs: A Researcher's Detour in Five Parts
An NLP evaluation researcher's honest map through the algorithmic, reward, and systems landscape of reinforcement learning for language models.