Like the show. But you’re the showrunner. All the drama. None of the property tax. A production-grade local app that turns a screenplay into a finished short film with synchronized video, native audio, dialogue, music, and subtitles. Powered by Google … Read more
6th June 2026 I’ve been experimenting with different approaches to running code in a sandbox for several years now, but my latest attempt feels like it might finally have all of the characteristics I’ve been looking for. I’ve released it … Read more
If you run Pi-hole, AdGuard Home, or any forwarding resolver, every one of your queries goes through one operator who sees both your IP address and the question. If you switch to a recursive resolver like Unbound, your IP gets … Read more
I’ve been experimenting with running local models on and off for a bit and I’ve finally found a setup that seems to work reasonably. It’s nothing like the output of a SOTA model, but the excitement of being able to … Read more
The HP C2089A “PostScript Cartridge Plus”, a 1991 add-on for the LaserJet II/III, adds PostScript Level 2 support through Adobe’s own reference interpreter (version 2010.118) on a 2 MB ROM. Thirty-five years on, that ROM is still a current PostScript … Read more
Apr 17, 2026 AIGame developmentCreationMCP I made a playable DOOM MCP app that can launch inline inside compatible AI clients like ChatGPT and Claude, and falls back to a browser URL everywhere else. DOOM running on Claude web MCP apps … Read more
I flew from London to Google Cloud Next 2026 in Las Vegas. Ten hours with no in-flight wifi. I used the time to test how far a modern MacBook can carry engineering work on local LLMs alone. Setup A week … Read more
Check it out! Here I am running a Minecraft server on a 1960s UNIVAC 1219B computer: Here’s a NES emulator rendering the first frame of Pinball: … and a selfie printed using the “overstrike” technique: We ran a ton more … Read more
Cloud AI APIs are great until they are not. Rate limits, usage costs, privacy concerns, and network latency all add up. For quick tasks like code review, drafting, or testing prompts, a local model that runs entirely on your hardware … Read more