> "I am interested to have end products with really good UX driven by peak performance and optimizations [..] Instead what I see is that everyone is in a race to have as much product out as possible by the same standards that applied to products made by humans"
AI is not equipped for this. Humans are part of the experience process, and AI doesn't "understand" individual humans better than other humans do.
UX relies very much on human psychology. That's why, despite all the efforts of scoring it, UX is not an objective metric:
1. AI doesn't know what "good UX" is, as this is judged by the sum of humans using it. --> Structured data of actual usage would be needed for AI to ingest, in a way that it can derive intent from every action and identify friction.
2. A "good UX" is not a transferrable metric. The best UX for a ticket vending machine is not applicable to video-editing software. --> AI would need to understand what to apply when, and at which point it needs to evolve its expectation to the user
3. A "good UX" is not an absolute metric. Photoshop/Premiere/... has a UX which was extended and refined over decades, it is considered good by experienced users but still overwhelmingly confusing for beginners. --> Someone would need to scope the AI for the correct target-group
All this is done today by doing extensive user-testing with actual humans. There are people experienced in this who can create better UX-designs from scratch than others can, and still we keep learning something when we put a group of humans in front of it and watch them use it.
"Intelligence" alone doesn't solve this.
I'm reminded of the story of Stephen Hawking's sister, telling how he invented a "better board game" as a child and always wanted to play it with her, which was apparently the most frustrating and boring game she ever played...
Then again, often when I specifically prompt my agent that "this works like shit, make it better" - it makes it better. There are for sure best practices that agents are well equipped to handle. Often the solution to make UX better is to just make the process simpler (for the user). Agents are also well equipped to do that.
I don't see any reason all the things you mentioned cannot be taught to an LLM using reinforcement learning. The newer models are already much better at this stuff, I see no reason that trajectory will change.
Not so. You can time how long it takes, how many clicks to goal, how much of the viewport is shown. There are so many metrics around UX and it can be approached in an objective way. So one UI can be evaluated on another for a given goal. Sick Fable on it and see.
> AI doesn't know what "good UX" is
Neither do ~80% (or more) of software developers.
Agreed. It seems everyone has forgotten who we’re building software for in the first place.
The idea of removing humans from the loop entirely feels like some sort of AI apocalypse.