Projects
Experiments, useful tools, and things I wanted to exist.
A hiring monitor that turns frontier AI job boards into analysis of current hiring activity and historical changes over time.
Paste any article URL for a clean, distraction-free reading view, then highlight any passage to start a threaded chat about that exact section.
A pass-through broker that hands your agent a disposable, read-only share address for Google Docs. No OAuth, no install, no signup - share a Doc, revoke anytime, just like with a colleague.
A link service built for agents. Every URL serves three response shapes from the same endpoint - an HTML stub for humans, raw markdown for agents, and full JSON - based on the request's Accept header. Skip the scraping, just hand your agent a link.
Phsyical trading cards based off of popular TBPN moments
A UX exploration combining radar charts and agentic work.
Meme site that allows you to open up as many vibe terminals you want.
50 LLMs battle it out on Snake.
I created a benchmark to test how well LLMs can recall information from a long context window. It was tested on gpt-4o & claude-2.1
In need of a physical project, I managed 3d printing, casting in bronze, and hand finishing maps of US mountains.
LLMs do better with shorter context windows. I built a tool to visualize how different chunking strategies to help you pick the one that is best for your use case.
