Hacker News Reader

Comment by Workaccount2 | Hacker News Reader

I desperately want an AI agent that can use my phone for me. Just something that takes instructs for each screen and execute it.

"Open Chrome"

"Go to xyz.com"

"open hamburger menu"

"Click login"

etc. etc.

View on HN

Isn't that what the voice a11y tools have been doing for years. Why do you need AI for that.

https://support.google.com/accessibility/android/answer/6151...

https://support.apple.com/en-us/111778

My friend that is AI. However, it can get a lot better: be more aware of screen content, follow multiple instructions at once, keep context in mind throughout the conversation and from past interactions

AI commonly means LLM. Where are you determining this is using a LLM for proccessing?

AI has existed for several decades before the first LLM was ever created.[1][2][3]

And that's not even considering machine learning and deep learning which also have existed for many years before LLMs.

Even if you consider the current usage of the word AI in popular culture, it includes things that are not an LLM like Stable Diffusion and Suno

[1] https://en.wikipedia.org/wiki/Expert_system

[2] https://en.wikipedia.org/wiki/Deep_Blue_(chess_computer)

[3] https://en.wikipedia.org/wiki/Lisp_machine#Historical_contex...

You must be new around here, kid. AI has been there since the birth of the programmable computer.

That’s all programmatic, you can’t throw curve balls at it.

I have this in my bookmarks:

https://dafdef.com/aikey

Droidrun did a Show HN recently. It's exactly that.

Reply on news.ycombinator.com