Hacker News new | past | comments | ask | show | jobs | submit

Show HN: Understudy – Teach a desktop agent by demonstrating a task once

https://github.com/understudy-ai/understudy
I have a hard time believing this is robust.
It's a really cool idea. Many desktop tasks are teachable like this.

The look-click-look-click loop it used for sending the Telegram for Musk was pretty slow. How intelligent (and therefore slow) does a model have to be to handle this? What model was used for the demo video?

Cool idea -- Claude Chrome extension as something like this implemented, but obviously it's restricted to the Chrome browser.
One more tool targeting OSX only. That platform is overserved with desktop agents already while others are underserved, especially Linux.
loading story #47355156
loading story #47355174
{"deleted":true,"id":47355086,"parent":47353957,"time":1773339799,"type":"comment"}
cool idea. good idea doing a demo as well.
[flagged]
loading story #47355526
loading story #47355122
[flagged]
loading story #47357102
2026 and we still pretend to not understand how llms work huh