blog

thoughts and writing

11 feb 2026

your brain already solved the problem ai agents need to work on

multi-agent memory

multi-agent memory architecture mirrors 500 million years of neural evolution. when you walk into your kitchen and your living room on the same day, your brain doesn't blend these into confused "memory soup". multi-agent ai systems are converging on the same solution.

read

12 jan 2026

should models always finish their sentences : the case for explicit hesitation

hesitation is all you need

the industry has spent three years optimizing for fluency, accidentally creating the world's most confident liars. we treat hallucination as a bug to be patched with more data when its a structural byproduct of our objective functions.

read