New comment by oleg2025 in "Computer Use is 45x more expensive than structured APIs"

oleg2025 — Wed, 06 May 2026 07:43:06 +0000

I've learned that compared to APIs, human interfaces are slow and messy, but there is actually a lot of science behind them. The good apps expose information well, and are optimised for clicks, typing, etc.

The best GUIs make great use of muscle memory, which makes them perfect candidates for scripting via CLI. eg a simple sequence "open Notes app, hit Cmd+F, enter search term, read list of results" can be one Bash command invoked by AI agent.

New comment by oleg2025 in "Computer Use is 45x more expensive than structured APIs"

oleg2025 — Wed, 06 May 2026 07:28:55 +0000

Couple of months ago I was inspired by kubectl, and built desktopctl CLI to control GUI apps. It uses combination of OCR and Accessibility API on Mac, represents UI as markdown, and exposes actions for mouse and keyboard.

My core idea was that "fast" perception loop is fully local, GPU optimised for UI tokenisation and change detection. "Slow" control loop requires LLM roundtrip, and uses token-efficient markdown interface in CLI output.

It uses relatively stable identifiers for controls, so agents can script common actions, eg `desktopctl pointer click --id btn_save` doesn't require UI tokenisation loop.

https://github.com/yaroshevych/desktopctl/tree/main

Hacker News: oleg2025

New comment by oleg2025 in "Computer Use is 45x more expensive than structured APIs"

New comment by oleg2025 in "Computer Use is 45x more expensive than structured APIs"