[HN Gopher] Generative UI and outcome-oriented design
___________________________________________________________________
Generative UI and outcome-oriented design
Author : marban
Score : 49 points
Date : 2024-04-04 08:00 UTC (2 days ago)
(HTM) web link (www.nngroup.com)
(TXT) w3m dump (www.nngroup.com)
| gedy wrote:
| > The Outcome-Oriented Designer - Because AI systems can shortcut
| the information-seeking process, the human design of
| microinteractions will become substantially less important.
| They'll either be inexistent (because the AI system makes them
| unnecessary), or they'll be dynamically designed through
| generative UI to fit the user's exact context and needs.
|
| Interesting ideas, though from companies I've worked with, there
| is a huge cadre of UX people that know nothing else and would
| likely fight this tooth and nail.
| threatofrain wrote:
| It also means that designers will own more responsibility and
| become closer to a researcher who is paired with a AI partner.
| It's an upgrade in prestige.
| greatpostman wrote:
| It basically means throwing out everything we know about ux
| design
| danielvaughn wrote:
| The more I learn about AI, the less confident I feel that we'll
| solve the bias and hallucination problems. A lot of these "in the
| future we will..." predictions assume a linear path towards
| progress, while the actual path is looking more and more
| asymptotic.
| MilStdJunkie wrote:
| Yeah, I've been monkeying around with an AI tool to help me
| query piles and piles of PDF files - bazillions of
| specification documents and suchlike - and if there's a single
| thing I've taken away from it, it's that I can't expect the
| same answer twice, even for questions that have just the one
| correct answer.
|
| That's all after preprocessing those PDFs, because there were
| some characters and sequences that blew up the works. That took
| some hunting. I _did_ learn that FOSI processors love injecting
| x00 null characters into the PDF for some godforsaken reason.
| Didn 't know that. Don't know _why_ , though, and probably
| never will.
|
| Falling back on older school techniques - from stats, text
| mining, topic models and other arcana - for some tasks is
| probably going to be worth it, for a while anyway.
|
| Most users can't use any of this stuff, it's too CLI-ish for
| the vast majority of the people doing actual work. I suspect
| this is the gap the OP is hoping to insert themselves into,
| that gap between these . . these so-called "AI" things . . and
| the average user, but they're going to need to do a better job
| of scoping out just how big a job that is.
|
| Now take all this with the following boulder o salt: we can't
| use any of the big cloud things, everything we do here has to
| be brewed up on prem, by people like me who do _not_ know what
| we 're doing. So we're not exactly AI superstars. Odds are
| everything I say is irrelevant for the outside world, with all
| your Geminis and whatnot.
| fragmede wrote:
| What's the tool? With temperature set to 0, the output should
| be reproducible, given the same input conditions.
| hansonkd wrote:
| A good GenerativeUI product depends on a datasource for the AI to
| have some working history to make decisions about what kind of
| interface to show a user.
|
| An A/B test needs thousands of samples in some cases to make a
| determination about which is preferred. A generative UI would be
| like running 100 simultaneous a/b tests for your users.
|
| I would think you would need a significant amount of traffic on
| the order of millions of users to be able to determine to some
| degree that one UI configuration is better for a particular type
| of user.
|
| Without the data to know what works the AI will essentially just
| be randomly generating UIs for each user.
|
| Defining an outcome is actually one of the hardest problems in AI
| and even in organizations. While you think startups can easily
| just say "make the UI that gets the most revenue" that isn't
| necessarily true. For example if a terrible user experience
| results in more short term revenue but your users die out, that
| isn't a good outcome for the company. Or maybe you have a free
| tier that you want people to use for network effect, etc.
|
| So it is very hard to have a single number to use for outcome. If
| every user has a different UI, then it also becomes hard to spot
| things that go against the company's interests, etc.
| batshit_beaver wrote:
| For an article about generative AI/UI, there sure is a lot of
| talk about recommendations and predictions.
|
| As another side note, the idea of a UI that changes every time
| you open the site/app is, frankly, ridiculous. Not sure what kind
| of UX researcher or even user would want that. Seems like a saner
| approach would be one of two worlds below:
|
| 1) Each app has a carefully designed foundation on top of which
| user-customizable components exist. This is already common, sans
| GenAI-powered component creation.
|
| 2) There is no longer a concept of an "app." Users instead
| interact primarily with a smorgasbord of APIs, via their highly
| personalized but temporally consistent, AI-assisted personal OS.
| Jonovono wrote:
| "As another side note, the idea of a UI that changes every time
| you open the site/app is, frankly, ridiculous."
|
| That's what we have _now_ , already. GenUI would be the
| opposite, where if you wanted, the UI could never change and it
| would stay the same if thats what you want.
|
| Totally agree the concept of apps will break down.
| jacobsimon wrote:
| That's a great point. Imagine you had an AI-based browser
| that could adapt any website into a consistent UI or reading
| experience.
| jayd16 wrote:
| Technically possible now, I suppose. If you're Google and
| have the analytics, you could make a standard site layout
| and munge every site into that format based on usage data.
| Neat idea.
| hansonkd wrote:
| Websites have spent the last 20 years removing user
| customizable functionality (think RSS feeds and making API
| private). While the tech may be possible, I don't see this
| being a reality without a major reversal in app development
| philosophies.
|
| Companies want to control what you see so they can control
| their revenue. Why would they want to expose their data and
| utility to UIs where they have limited ability to monetize?
| g8oz wrote:
| Firefox Reader mode does a decent job of this.
| rzzzt wrote:
| We already had a considerable subset of the required APIs
| exposed in Web 2.0 times. I don't see it coming back any time
| soon, despite the integration work it enabled being lots of fun
| and also genuinely useful.
| willsmith72 wrote:
| Nice idea, and I love outcome-oriented design. There's so much
| time wasted, especially in startups, on minute UI details which
| almost certainly have 0 measurable impact. But I don't really
| agree you need generative ui
|
| > This individual example may be plausible without genUI, but not
| at scale.
|
| Nothing about that example seems implausible at scale. It's just
| a combination of personnalisations, saved settings, and learnt
| user preferences.
|
| Maybe no one puts that particular example together to that level
| today, but there's nothing stopping someone doing it today
| without generative ui.
| andybak wrote:
| > However, in the short-term, we anticipate quite a few problems
| and challenges.
|
| For some values of "short-term" and "quite a few"
| jayd16 wrote:
| Good luck helping your grandma over the phone now. Stack overflow
| or even a video tutorial? Useless.
|
| Seems like predictable should beat customized for something like
| a gui.
| mihaic wrote:
| The big issue I see with this type of personalization of UI is
| how much worse I would become at helping others to get things
| done, since my muscle memory for an interface would have been
| made for my UI.
|
| This lack of shared similarity in the workspace is also another
| big issue with Apple Vision for instance, but nobody really uses
| it more than a few hours to get to this realization.
| mateo1 wrote:
| This is not about improving your experience. This is about
| getting end users to behave a certain way. If you have a
| gambling or trading app, you could automatically adjust the UI
| based on your end users psychological/behavioral profile,
| gradually over time, to put the more profitable/higher risk
| option in more prominent/more likely to be used positions. Or
| maybe your user clicks "block access" by muscle memory and your
| AI based predictor finds out that if they replace the block
| button with the allow button users now click allow way more.
| Big success. I can't wait to see how much more value we can
| extract from people by controlling their behavior through UIs.
| troupo wrote:
| This article is a nothingburger attempt to capitalize on the AI
| hype.
|
| None of it makes any sense if you stop to think about it for even
| a second. Anything from ever-changing UIs to the actual state of
| AIs to the basic systemic issue that you can't properly describe
| all the outcomes a person needs from a product without it being
| self-contradictory (and ever changing to boot).
|
| Edit: this will not stop multiple startups from chasing VC money
| using this idea
| GrinningFool wrote:
| The most important rule I've learned for interfaces (UI - but
| also API and others) is that they should be self-consistent with
| no surprises. The user learns what to expect and they can rely on
| it, which generally makes it easier for them to navigate and get
| the results they want.
|
| It seems to me that a generated UI does the opposite of that, and
| leads to a lot of uncertainty...
|
| ... How does support help them, or even troubleshoot problems
| when the user describes what they saw and did?
|
| ... How can one person instruct another in accomplishing a task
| when the interface is different?
|
| ... How can you document the instructions for accomplishing
| specific goals?
|
| ... How user-unfriendly is a UI that not only changes per user,
| but could change over time as more data is gathered about how the
| user is interacting? Especially if the user needs to do something
| out of the ordinary [for them], the means of doing it can get
| buried over time.
| visarga wrote:
| > they should be self-consistent with no surprises
|
| And LLMs are exactly what is needed - they know the consistent
| and no-surprise answer to anything. The UI will adapt to serve
| your needs, that's how it can help you. The web we see today is
| full of dark UI patterns and junk content. A generative UI
| could filter, rank and present the pile of garbage in a clean
| form.
|
| Social networks and big website operators control what we see,
| in what order we see it, and how it is presented. All of them
| carry vectors of attack. They abuse the public. For example FB
| was always changing where it put various user settings, and
| resetting them from time to time.
|
| An AI agent that creates a generative UI can guard your
| preferences. I see these gen-UI agents as running locally in
| privacy. They interface with the web to interact and gather
| information, and distill it into bespoke UIs. They overrule all
| the power games publishers played with users and try to prevent
| users inadvertently leaking private information, an AI
| firewall, especially needed now that the web will be filled
| with synthetic text and other AI agents. Few people will still
| look at the raw web, we will wear a protective mask of gen-UI.
| FridgeSeal wrote:
| LLM's struggle to return the same answer twice, and now
| you're suggesting they'll magically and consistently mediate
| UX and API differences? I have a hard time believing that.
| _Adam wrote:
| >Outcome-oriented design involves orchestrating experience design
| with a greater focus on user goals and final outcomes, while
| strategically automating aspects of interaction and interface
| design.
|
| Dark patterns is another type of "outcome oriented design" where
| the outcome is the user subscribing/not canceling/paying
| needlessly. Adding "strategic automation" will doubtlessly just
| make this problem worse.
| g8oz wrote:
| This article is exactly the type of empty handwavy thought
| leadership being pushed by every outfit seeking to capitalize on
| AI. I'm sure many lucrative consulting engagements will follow.
| jdpigeon wrote:
| Yeah. Unclear after reading this whether anything meeting their
| definition of GenUI actually exists or whether this is just
| speculation
| victor106 wrote:
| Completely agree.
|
| But unfortunately this is a sure shot way to rake in the big
| bucks. Lot of companies budgets are unfortunately still
| controlled by people who fall for buzzwords and who don't have
| the time or inclination to look a bit deeper and understand
| core concepts and tradeoffs. So they refuse to look at things a
| little critically.
| aatd86 wrote:
| Can't even borrow someone laptop anymore... The UI is
| different...
|
| I doubt that UIs are going to be tailored to every and each
| person.
| dexwiz wrote:
| Can't help but feel that is a bit like saying can't go to
| another website, the UI is different.
| FridgeSeal wrote:
| So the AI will console some information, and make _some_ kind of
| UI, the _some_ decisions about layout, and functionality and
| magically adapt?
|
| Yeah this is going to be so great for usability. "Where did the
| "foo" button go?" Oh right, the AI has magically decided I am
| better off with it somewhere else. "Why did the interface change
| completely today?" Oh right, the AI is having a moment. This
| feels like a usability nightmare.
|
| This screams upper-management consultancy, doesnt value the work
| that goes into design and UX and would love to cream some money
| by pretending they could fire an entire department.
| fragmede wrote:
| Microsoft Office already did the ribbon thing. Time to try it
| again?
| upsidepotential wrote:
| Increasingly likely that UI evolution will prioritize a shift
| from a "click"-centric approach to one that's "command" oriented.
| This means AI agents interpreting your instructions and executing
| task processes, rather than continually reconfiguring the UX to
| match your preferences. High computing costs with AI also favor
| instruction-to-task completion dynamic, not just indulging in
| elaborate screen layout adjustments.
| AlienRobot wrote:
| Take a look at one of the linked services https://canonic.dev/
|
| This is what the future looks like, but without dragging and
| dropping.
|
| It's just a bunch of blocks stacked in grids, columns, and rows.
| This is what GUI and UX has become. Just black text on white
| rectangles, because it needs to adapt to every form factor, be
| accessible, be internationizable, be
| blahblahblabhlabblahblahblah. It has to be generic.
|
| GenUI is the next step in a very depressing trend of sucking out
| all the color from websites and applications, and just the
| thought of it happening makes me very sad.
|
| I'd have a much better "user experience" if I found a website
| that turned my cursor into a sword.
___________________________________________________________________
(page generated 2024-04-06 23:00 UTC)