Remix.run Logo
▲ rickdeckard 3 hours ago

> "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...

▲daveads5 an hour ago | parent | next [-]

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.

▲c-linkage 21 minutes ago | parent [-]

We don't build modern software for humans. We build it for profit extraction. It's why the modern cycle is:

  1) First-mover wins: burn VC capital to get a product out free
  2) Establish brand and market dominance
  3) Integrate advertising to keep the product free and grow the user base
  4) Crush competition and capture users due to "mind share" and "network effects"
  5) Enshittification until no one is happy with your product and making a replacement is impossible
▲jaapz 3 hours ago | parent | prev | next [-]

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.

▲MattRix an hour ago | parent | prev | next [-]

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.

▲rickdeckard an hour ago | parent [-]

Hence I wrote: "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."

The challenge is more about providing actual, objective data to learn this.

The LLM will not be able to decide what is "good UX" and "bad UX", it will have to ingest this information in vast detail from judgement provided by humans, which is also varying alot.

Case in point: Coming from that field, I personally don't have a good user experience using iOS, a majority of end-users will strongly disagree.

An LLM would need to be trained to handle both cases to judge the same human interface, so it would need alot of data to understand both views...

▲adrianN 36 minutes ago | parent [-]

The human UI designer has the benefit of being and to run experiments on themselves, but only n=1. for any problem where that is insufficient or even misleading that benefit disappears. I’d argue that UI is an area where you need n>>1.

▲swader999 2 hours ago | parent | prev | next [-]

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.

▲rickdeckard an hour ago | parent | next [-]

I frankly assumed the example of vending machine vs video editing software illustrated how this is not the answer.

A perfectly scoring vending machine UX applied on Adobe Premiere will tank the UX for Premiere users.

▲jpc0 an hour ago | parent [-]

Unrelated but as someone who has used several NLE Adobe Premiere is not what I would pick for good UX.

▲ninjalanternshk 43 minutes ago | parent | prev | next [-]

Those are ways of optimizing patterns we already use. New UX patterns from the simple like object rollover states, to the complex like the iPod click wheel, take human innovation.

We respond with delight or disdain based on how they feel.

The only way for AI to know how humans feel about something is to be trained on what we’ve already said about it.

▲FridgeSeal 2 hours ago | parent | prev [-]

I do so suspect that harebrained ideas like this is how we got “fully optimised, completely garbage” UX experiences that are present in some major corporate services. Google/youtube being a good example of this.

▲swader999 2 hours ago | parent [-]

Of course discretion is needed. It's just another tool at our disposal.

▲cicko 2 hours ago | parent | prev [-]

> AI doesn't know what "good UX" is

Neither do ~80% (or more) of software developers.

▲krige 2 hours ago | parent | next [-]

Doesn't make me any keener to use AI. In fact, the opposite.

▲sedictious 3 minutes ago | parent | prev [-]

Why is it always a race to the bottom?

"AI does X kinda bad" "Well most humans do X even worse so shut up and eat it up"