Comment by deergomoo | Hacker News Reader

Comment by deergomoo | Hacker News Reader

One thing I have found very odd about the current wave of AI tools is that there seems to be an unspoken element of giving up and admitting failure in other areas of computing.

Programming copilots are often sold on how they can automate drudgery and boilerplate, which implies we are incapable of or uninterested in designing programming languages, tools, and patterns which do not require boilerplate or drudgery.

Teaching models to use traditional GUI apps implies we have given up on or are not even bothering to create proper hooks for an automation system to utilise.

Something about it feels wrong to me, because it bakes existing inefficiencies into the system. Can we really not solve the inefficiencies instead of pouring unfathomable amounts of compute into working around them?

This is not a computer problem, it's a human one. It's not that we don't have APIs and hooks because they're so difficult to implement - we don't have them because software producers don't want or care for us us to have them.

Enabling automation will never be zero effort and anything more than zero effort for something with such a low ROI is a no-go by default. But increasingly, automation is actually seen as a danger to their business models and companies sometimes even go out of their way to prevent it.

Looking at the screen the same way a user does is the only way to win.

Focusing on the GUI applications: There have been a few GUI automation solutions over the years - since the post's software is from MS, I'll take UI Automation as an example. Works well with Win32 controls, not sure how well it works with the XAML-based toolkits.

But not all software is written with those UI frameworks. Some use different widget frameworks, some immediate GUIs, others just render a webpage and either use HTML or fully render the controls themselves. And without everybody using the same standard, the only standard we have for parsing their output is the pixels they render to.

Computer based agents have no limits, that’s the advantage. Sure a proper automation hook is better if its available, but a lot of the time it isn’t, either due to lack of resources or monopolistic behavior

Reply on news.ycombinator.com