memos

reflections on building in AI. written when something is worth saying.

why most AI products are measuring the wrong thing may 2026

the metrics that made sense for web apps are being applied to AI systems that work completely differently. that mismatch is hiding a lot of problems.

what running LLMs locally taught me about abstraction apr 2026

when you remove the API layer and run things yourself, you see things you were previously just trusting someone else to handle. some of it is reassuring. some of it isn't.

the gap between benchmarks and actually useful mar 2026

a model can top every leaderboard and still be frustrating to work with day to day. i've been thinking about why that gap exists and whether it's getting smaller.

on building things you can't fully explain yet feb 2026

some of the most interesting things i've built started as a feeling that something was wrong or missing — not a clear idea. i'm trying to get better at following that instinct earlier.

learning something new from the inside out jan 2026

the way i learn anything is to build something with it. i don't think there's a faster path to actually understanding. the hard part is getting comfortable being wrong in public while you're doing it.