In this issue
October 2026
Codex + Ollama: an easier route to coding with local LLMs
I reran my COLD STORAGE local-coding adventure game experiment with Codex and Ollama, using gpt-oss-20b and DeepSeek V4.1 Flash. I used an identical prompt for each and came up with comparable results and an easier path to local coding for people not as familiar with CLI.
Try Monster Scanner, my iOS local LLM Halloween toy/game on TestFlight
My local LLM Halloween game is still waiting on App Store review, but the beta is open on TestFlight.
A quick start guide to coding with Pi and Qwen locally
Based on feedback from my Pi on a local model workshop: a one-slide quick start guide to running Pi and Qwen for local coding on a Mac.
Monster Scanner: LLMs on an iPhone, Halloween edition
I wanted to try creating an iPhone app that used an open-source LLM hosted on the iPhone itself. For the demo, I made a fun and silly offline Halloween party game using a Qwen vision-language model hosted on an old iPhone 14 Pro.
Pi on a local model: a field guide for Claude Code users
You can run a genuinely useful coding agent entirely on a laptop. A workshop on the Pi coding agent with Qwen3.8-27B, for developers who use Claude Code every day.
COLD STORAGE: a haunted data center adventure
An Infocom-style text adventure in Python, written entirely by a local model on a 96GB MacBook Pro. No cloud APIs in the loop.
September 2026
Inside Voice
Talk instead of type, on your Mac. Hold one key, say what you mean, let go: your words appear wherever you were typing. Nothing you say ever leaves your computer.
January 2026
Transmission
Been pasting Calvino’s Invisible Cities verbatim into Genie, and it works surprisingly well.
June 2025
LLM Evaluation Mini-Hack: build better benchmarks
A morning hack where the RMAIIG AI Engineering group built its own open-source LLM benchmark and evaluation suite.
January 2024
Welcome to MrFuture.com
Why I'm starting a blog, and what you'll find here: talks, projects, experiments, and what I learn along the way.