News for hackers. Stuff that matters.

A comment on UFO: A UI-Focused AI Agent for Windows OS Interaction.

Re:UFO: A UI-Focused AI Agent for Windows OS Interaction by dartharva on Saturday February 17, 2024 @03:24AM (#39407546)
Does it support other visual-input-accepting language models? GPT-V is paywalled.
[ Parent | on HN ]
Re:UFO: A UI-Focused AI Agent for Windows OS Interaction by dartharva on Saturday February 17, 2024 @07:52AM (#39409001)
Update: no, it doesn't as of now.
[ Parent | on HN ]
Re:UFO: A UI-Focused AI Agent for Windows OS Interaction by Deverauxi on Saturday February 17, 2024 @09:34AM (#39409742)
The code isn’t very complicated. You could edit in any vision model you want:

https://github.com/microsoft/UFO/blob/main/ufo/llm/llm_call....

[ Parent | on HN ]
Re:UFO: A UI-Focused AI Agent for Windows OS Interaction by dartharva on Saturday February 17, 2024 @11:33AM (#39410944)
I don't have the resources currently but would love to test something like LLaVA out for this, but I won't keep my hopes up.
[ Parent | on HN ]