Controlling Vintage Mac OS With AI

March 12, 2026 by Lewin Day 11 Comments

Classic Mac OS was prized for its clean, accessible GUI when it first hit the scene in the 1980s. Back then, developers hadn’t even conceived of all the weird gewgaws that would eventually be shoehorned into modern operating systems, least of all AI agents that seem to be permeating everything these days. And yet! [SeanFDZ] found a way to cram Claude or other AI agents into the vintage Mac world.

The result of [Sean]’s work is AgentBridge, a tool for interfacing modern AI agents with vintage Mac OS (7-9). AgentBridge itself runs as an application within Mac OS. It works by reading and writing text files in a shared folder which can also be accessed by Claude or whichever AI agent is in use. AgentBridge takes commands from its “inbox”, executes them via the Mac Toolbox, and then writes outputs to its “outbox” where they can be picked up and processed by the AI agent. The specifics of how the shared folder work are up to you—you can use a network share, a shared folder in an emulation environment, or just about any other setup that lets the AI agent and AgentBridge access the same folder.

It’s hard to imagine any mainstream use cases for having a fleet of AI-controlled Macintosh SE/30s. Still, that doesn’t mean we don’t find the concept hilarious. Meanwhile, have you considered the prospect of artificial intelligence running on the Commodore 64?

Illustrated Kristina with an IBM Model M keyboard floating between her hands.

Keebin’ With Kristina: The One With The Keyboard-Mouse, Again

December 29, 2025 by Kristina Panos 8 Comments

The astute among you may remember an earlier version of this Russian beauty, the Lapa, which I featured last year around this time. Creator [lemosbor] claims that the worry was less about visual beauty and more about ergonomics. Way more. Well then, let this serve rather nicely as a textbook definition of that old form-follows-function principle.

A splendidly ergonomic split with few keys, large openings under the palms and wrists, and mouse control on the thumbs. — The lovely Lapa.

See, [lemosbor] believes that the keyboard must adapt to the hands and not the other way around. The main goals were to minimize hand and finger movement as well as the visual attention required of the keyboard itself. No, there were never going to be any screens or RGB, and there likely never will be.

But I refuse to sidestep the obvious beauty in this keyboard, which from the side resembles a stylish and expensive pair of slightly-heeled shoes that were tailored to the contours of the human hand. And let’s not forget those handmade, oval keycaps, which again are a product of form-follows-function.

Continue reading “Keebin’ With Kristina: The One With The Keyboard-Mouse, Again” →

All System Prompts For Anthropic’s Claude, Revealed

October 12, 2024 by Donald Papp 5 Comments

For as long as AI Large Language Models have been around (well, for as long as modern ones have been accessible online, anyway) people have tried to coax the models into revealing their system prompts. The system prompt is essentially the model’s fundamental directives on what it should do and how it should act. Such healthy curiosity is rarely welcomed, however, and creative efforts at making a model cough up its instructions is frequently met with a figurative glare and stern tapping of the Terms & Conditions sign.

Anthropic have bucked this trend by making system prompts public for the web and mobile interfaces of all three incarnations of Claude. The prompt for Claude Opus (their flagship model) is well over 1500 words long, with different sections specifically for handling text and images. The prompt does things like help ensure Claude communicates in a useful way, taking into account the current date and an awareness of its knowledge cut-off, or the date after which Claude has no knowledge of events. There’s some stylistic stuff in there as well, such as Claude being specifically told to avoid obsequious-sounding filler affirmations, like starting a response with any form of the word “Certainly.”

Continue reading “All System Prompts For Anthropic’s Claude, Revealed” →