Introducing TYO Reach: A Travel Companion for Your Browser
TYO Reach is a lightweight traffic proxy for a single browser — a handy travel companion for reaching the everyday sites and apps you rely on at home when they quietly stop working abroad.
Read more...
Introducing reach-dl: a Local, Private Download Manager for TYO Reach
reach-dl adds a side-panel download manager to your browser that saves the video you're watching — through your own TYO Reach gateway, with your own login, entirely on your own machine. No server, no cloud converter, no cookies leaving your computer.
Read more...
The Model That Aced Olympiad Math Can't Write a Tweet
The 4 GB series found a 3B that reasons like a giant. So surely it can write? It can't — and how it fails is the interesting part. VibeThinker-3B chokes on a 120-word story while two plain instruct models a fraction as clever nail it, and a language twist decides which one you want.
Read more...
You Don't Need to Be Bunnings to Build an AI Assistant
When Bunnings launched 'Buddy', an AI shopping assistant, it looked like something only a national retailer could pull off. We built the same kind of thing for a small networking store in about a week, out of parts most businesses already have. Here is what an AI store assistant is actually made of — and why the language model is the easy part.
Read more...
The 4 GB Card You Already Own Can Reason Now
The dispatch experiment ended on a question: route the hard tail to a more capable model — but which one, if you do not want to reach for the cloud? VibeThinker-3B, a 3B reasoning specialist, runs entirely on the 4 GB laptop GPU you probably already own, solves competition math the workhorse cannot, and sips about 50 watts doing it.
Read more...
The Small Model's Real Job Is Dispatch, Not Work
We pushed a 4 GB laptop model past coding into reasoning, extraction and writing to find its limit — then measured a better use for it entirely: not doing the work, but routing it. A reasoning-tuned 1.7B model covers 90% of a general workload, and a perfect router is 74% cheaper at equal quality.
Read more...
What a Native Tool Call Actually Is
An LLM only ever outputs text — so how does an AI agent run a tool? The answer is the native tool call, a precise, trained, parseable protocol that most people hand-wave over. Here is exactly what it is, what happens on the wire, and why a small model that knows what to do still cannot make one.
Read more...
The 4 GB Experiment: What Actually Makes a Small Model a Good Coding Agent
We stopped theorizing and ran ~900 trials on a 4 GB laptop GPU to measure what makes a small local model a good coding agent. The result overturns intuition: the edit format and the editor model decide almost everything, the clever agentic scaffolding mostly hurts, and the simplest setup won.
Read more...
How a Coding Agent Actually Writes Code
The first four posts in this series took the telescope view of AI agents. This one takes the microscope: how a coding agent turns an instruction into a working, tested change — how it edits, compiles, runs, tests and debugs — and why Claude Code behaves like a native *nix programmer while others reach for a throwaway script.
Read more...
The Coding Agent Shootout and the Best Harness We Could Not Read
After reading the source of five open coding agents — OpenAI's Codex, Pi, OpenCode, Kimi Code and Gemini CLI — here is how they actually stack up, strengths and weaknesses, which one wins, and why the best harness of all belongs to a tool we deliberately left out of the code study: Claude Code.
Read more...