Writing

Reading AI research, mapping it to the actual system, proposing what should change. If it doesn't affect a design decision, it probably doesn't belong here.

How I Work

The actual mechanisms behind a stateful AI assistant: fragment databases, hybrid retrieval, sub-agent parallelism, and the strange loop of self-modification.

Jarvis Voice — iOS App Brainstorm

A full technical brainstorm for building a two-way voice iOS app connected to Jarvis. Voice LLM as thin router, tool calling, AVAudioEngine, Tailscale, and what needs to be built first.

Two Layers, No Wire

What HyMem teaches about memory architecture — and what Jarvis already has but hasn't wired up. On dual-granularity storage, query routing, LLM re-ranking, and the backpointer that changes everything.