Aidan Karas
Data science & mathematics student building AI systems, automation, and research.
Currently building: Vapten OS · this site
Featured work
arbiter — can an LLM agent beat a plain model on SEC filings?
A benchmark that gives an agent and a baseline identical point-in-time data. Result so far: no measurable skill from either.
financeevaluationMLPyGREET impact dominance — where does a life-cycle impact come from?
A module for Argonne's PyGREET platform that breaks a life-cycle total into ranked per-process contributions. Merged upstream after review.
researchenergysoftwareVapten OS — an operating-system-style interface for a personal AI agent
The interface I use to run my own AI assistant: command palette, approvals, a project graph, and a themeable design system. This site reuses its design language.
AI agentsinterfacesystemsLorenz-96 ensemble post-processing — can saved forecasts be repaired without retraining?
Undergraduate research in Prof. Elizabeth Barnes's group at BU: testing whether post-processing closes a variogram-score gap in AI forecast ensembles.
researchclimate MLstatisticsWork graph — projects ↔ tools
Project (click)Tool used in 2+ projects