Can a small VLM tell you if you can park in San Francisco? A parking-sign benchmark plus QLoRA-tuned 3B and 7B students that read the pole; a deterministic resolver does the logic.
7B student reads real SF sign poles at 0.83 F1 (base: 0.22); verdicts right ~0.9 via the resolver
A local-first library for the stuff you make with AI. Index, search, preview, and share your work, then use your past output as the style guide for the next thing you build.
Published on PyPI, pip-installable
A gamified app that teaches reinforcement learning across six levels of PufferLib games, with interactive in-browser training, concept visualizations, and an XP system.
6 playable levels, train models live in the browser
An endless runner set in Old Delhi: dodge rickshaws, outsmart monkeys, grab samosas, and make it to the Red Fort. Playable on desktop and mobile.
Playable at shubham.gg/chandni-bros ↗
Poker meets Gwent in a medieval tavern: build poker hands across two rows, manage a 10-card budget, and outlast the house across a best-of-3 match.
Single-player strategy card game, playable in the browser
A cozy, Pokémon-style browser RPG about walking the world's villages and letting culture arrive sideways: through soup, slang, and the small corrections people give you. No combat, no timers, nothing to lose.
Ten illustrated chapters across five continents, with generative art and nine regional music styles