COLM 2026
CHI 2021 · Best Paper Honorable Mention (top 5%)
An experiment in making the grokking phase transition — where models suddenly generalize long after memorizing — arrive sooner.
Reverse engineering a 2001 GameCube game to inject dynamic AI dialogue via memory mapping — no game code modified. Watch the demo →
An XGBoost model on ten years of crash data, mapping the hidden geometry of risk in Austin's cycling network.
A scrape-clean-finetune pipeline on viral science videos that took a channel's click-through rate from 5% to 15%.
Testing LLM reasoning against ancient paradoxes of vagueness. Do models understand "heaps" of sand?
A browser extension that replaces every ad on the internet with fine art from public museum and NASA collections.
A keystroke-golf game inside Vim: transform the starting text into the target in as few keystrokes as possible, scored live against a leaderboard.
A minimalist bullet-journal task manager that lives in Vim.
Sign the guestbook and I'll email you when a new paper or post goes up. No spam — pinky promise.