Hacker News new | ask | show | jobs
by aitchnyu 264 days ago
A few of them imply a vision model which can control your keyboard and mouse. Offline-only of course.

It could help with most tech support questions.

We could select text and ask to fact check or explain to layperson or search more.

It could get around cookie banners and dark patterns.

It could do my time tracking and tell me to get off HN and optimize Pomodoro-style breaks.

It could write scripts after watching me switch between multiple pages of AWS services.

1 comments

> It could write scripts after watching me switch between multiple pages of AWS services.

Feeling this one hard. Especially frustrating given how AWS has introduced multiple competing (mediocre) services to do this and they are all difficult to either discover and setup, or chat-based (Q).