Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

github.com

Post reply on HN
Print view View original

31–40 of 66 posts

Re: UFO: A UI-Focused AI Agent for Windows OS Interaction

#33

Post by tiborsaas »

smashah wrote: post #22

If anyone else did this then some useless lawyer would be activated from their slumber to send out OSS devs cease & desists based on supposed violations of sacred terms and conditions. This project is the future that we were promised but it is under threat by supposed legal challenges. What if the demo asked the email to be sent as a message via whatsapp desktop instead? That would (according to their anti-freedom la…

I don't understand why anything in the demo would count as T&C violation. Who would be offended on what basis? If I can automate my desktop with a preprogrammed script, then this is not different.

Re: UFO: A UI-Focused AI Agent for Windows OS Interaction

#34

Post by klabb3 »

smashah wrote: post #22

If anyone else did this then some useless lawyer would be activated from their slumber to send out OSS devs cease & desists based on supposed violations of sacred terms and conditions. This project is the future that we were promised but it is under threat by supposed legal challenges. What if the demo asked the email to be sent as a message via whatsapp desktop instead? That would (according to their anti-freedom la…

Rules for thee not for me. Scraping for instance is bad only when other people do it.

Technically speaking though, user facing websites are built with quite weak UI accessibility in mind. Partly to prevent others bots from using it. I worry less about the LLM/AI particularities, and more about adding yet another comprehensive layer to the stack. It’d not exactly be standing on solid foundation.

During the 2010s Web 2.0 there was a brief moment where open APIs and such were trending, which was a bit of rejuvenation of interoperability across companies, domains, applications etc. To simplify we can call it cross-app interactions, like auto hotkey, Automator, etc. An LLM controlled broker falls in that domain as well. But now that “closed binary fuck you” model came back industry wide, it’s almost impossible to build such things. (It’s hard enough to build integrations when people are cooperating. When they’re actively adversarial, things generally break quickly, if they work at all)

Re: UFO: A UI-Focused AI Agent for Windows OS Interaction

#38

Post by dartos »

klabb3 wrote: post #34
smashah wrote: post #22

If anyone else did this then some useless lawyer would be activated from their slumber to send out OSS devs cease & desists based on supposed violations of sacred terms and conditions. This project is the future that we were promised but it is under threat by supposed legal challenges. What if the demo asked the email to be sent as a message via whatsapp desktop instead? That would (according to their anti-freedom la…

Rules for thee not for me. Scraping for instance is bad only when other people do it. Technically speaking though, user facing websites are built with quite weak UI accessibility in mind. Partly to prevent others bots from using it. I worry less about the LLM/AI particularities, and more about adding yet another comprehensive layer to the stack. It’d not exactly be standing on solid foundation. During the 2010s Web 2…

I’ve worked on many sites over the past 10 years.

Never once was the conscious decision made to not be accessible to prevent bots from scraping.

Re: UFO: A UI-Focused AI Agent for Windows OS Interaction

#39

Post by dartos »

userbinator wrote: post #16
tflol wrote: post #10

have they fixed teams yet? that app that like the entire united states uses for pc work every day? i still cant copy paste a code block, or copy paste literally anything. i think microsoft should use AI to learn how to code code blocks in chat or they should ask chatgpt how to use the clipboard of their own OS

MS Teams is exactly what I'd expect from an AI-generated app --- barely working, lots of little bugs and general oddness, and overall a mediocre experience.

Isn’t teams quite an old product?
Post reply on HN