Notes on AI research, agent security and distributed systems.
Neuron Dissector opens up a small story-writing model in your browser, every neuron and attention head on screen as it writes, with a scalpel for mechanistic interpretability's basic moves: ablation, activation steering and a per-neuron logit lens. A neuron that waits for a girl, a lobotomy that writes “good” forever, a palace neuron that leads to mud, and the GPT-Neo forward pass written from scratch to hold the knife.
Llama-Doorman-22M: a 22M-param on-device classifier that catches ~2× more missed prompt injections than frontier models, and the use-vs-mention dataset, eval harness and selection rules behind it.
I measured before rewriting anything: the page stays JavaScript, but a 2.9 KB Rust kernel for matrix × vector runs 13–19× faster than the JS loop it replaces and makes the language models running in this site's browser apps 3–5× faster end to end, with the same results. Benchmarks, the memory rules that took most of the work, and what WebAssembly can't fix.
A small Cloudflare Worker that polls the status pages of the clouds and model providers we depend on every ten minutes, keeps only the incidents that touch services we use, and posts each one once in Slack, with its updates threaded underneath.
My IEEE ICC 2026 paper: edge caches that serve quorum-signed snapshots, regional BFT clusters that only handle changes, and a global DHT that is always there. Central-indexer latency with 99.95% availability when the edge goes down.
Live marketplace comparables ranked by Levenshtein distance and priced by their median, a daily catalogue crawl to target the right products, then an ML layer: quantile price models trained on what actually sold, sales-velocity prediction and embedding-based product matching.
A stateless API, a queue-backed solver fleet on Azure and a scenario cache that removes 97 per cent of the arithmetic: how a 27-hour Monte Carlo availability study became a 62-second click, and the ML layer that learns from that cache where to start solving.
A 100,000-iteration Monte Carlo availability study and capacity ramp-up planning built into the app, with the GASBOL pipeline redesigned as a case study: system availability from 0.9811 to 0.9997 with stand-by units.
Packaging a gas-pipeline thermohydraulic solver as an app for iOS, Android, desktop and the web: hundreds of simulations in seconds, executive and technical reports, XML models and KML for Google Earth.