Personal website and public archive for Pleometric. I use this site to archive what I read, watch, and study. I also write about my research interests. Each resource has a short annotation explaining why I saved it.

RECENT

2026-02-13 LINK Elhage, et al.
I'm catching up on current mechanistic interpretability work. Neel Nanda recommends this paper as a check on how well you understand transformers.
interpretabilityAI
2026-02-13 LINK Christine Kozobarich & Ophira Horwitz
AI Village is an ongoing experiment in multi-agent systems, where computer use agents are given broad goals to work toward and anyone can observe their dynamics. The article highlights some interesting behavior from the Gemini family of models
model behaviorAIGeminiAgent

PAPERS

2026-02-13 PAPER Alex L. Zhang, Tim Kraska, Omar Khattab
I'm seeing frequent backlinks to this as a potential next step from reasoning models, especially when it comes to tool use
AIAgentsInference-Time ScalingLong ContextRecursive Decomposition