* There will be a monthly fee for the interface; you owe the monthly fee as long as you have it, so you need surgery to stop paying
* When you download knowledge, it's a rental, and in addition to per-hour rental fees and the network connection fee, you will owe 30% on the value of whatever you create
* The TOS will govern your behavior continuously, since you're always using the interface
* Your behavior will always be monitored because it's totally justified to spy on you all the time just because you borrowed pottery knowledge
* If you're found to be in violation of any part of the TOS at any time, they will erase all of the knowledge they've added to your brain, as well as any derived knowledge you gained through the use of their knowledge
* Because this product isn't actually considered essential, you will have no legal remedies if they turn it off, even if you are not actually in violation of the TOS
I am being a little facetious, but you made a bold claim.
But keep in mind that during the sim, you'll be able to ask the computer what you want the plane to do, and the computer will magically make it happen on your display.
It’s gonna take the fun out of the experience a little bit though!
It feels like being one of those Futurama heads in a jar that can’t do anything by themselves.
For now almost all applications of ChatGPT happen in chat windows because it requires no further integration, but there's no reason to expect things will always be this way.
I hate the idea of having to use a mouse to click on a visual GUI to navigate a file system in order to make use of its functionality.
It's less the case today, even among developers, but it wasn't that long ago that I remember that any serious technical user of a computer took it as a point of pride to touch the mouse as little as possible. They're also still correct in that thinking. The command line is a very powerful UI with lots of benefits and while the mouse makes navigating the OS easier it's still much more limited than command line usage.
Touch screen interfaces are another example of an easier UI that ultimately feels even more limited. But people still plug their iPad pros in to magic keyboard folios frequently.
Having worked with these tools everyday for awhile now the "AI will change UX" is such a better take than "AI will conquer the world!". AI does fundamentally open up new work flows and user experiences, many of which do over a lot of potential improvements over their predecessors.
At the same time I doubt we'll see a world where we don't end up using the command line for the majority of serious technical work.
Depends o the use case. Touch screen is much more powerful than command line for maps, for example. Or for drawing. Mouse + keyboard is much more powerful than just keyboard for DAWs. And so on and so on.
Ironically, studies have shown that mouse-based interfaces are more efficient for practically all filesystem use-cases compared to CLI interfaces.
Despite objectively faster-time-to-solution, people self-report that they "feel" that the mouse GUIs are slower.
That's because there's fewer actions per second when using a mouse. It's a smooth gliding motion and then a single click, versus many keystrokes in a row with a CLI.
Rapid actions feel faster, even if it takes more wall-clock time to achieve a task.
Keep this in mind next time you sneer at a "bad graphic user interface" for being "slow".
For your use case, on macOS open Automator.app and add three actions
1. "ask for finder items" (the source folder)
2. "filter finder items" (by name)
3. "copy finder items" (to target folder)
Repeatability and configurability is where the GUI action shines. With only one click more you can
- add filtering by size, opening date, modification date, etc. in addition or a combination thereof
- do the same action for multiple source folders and the same target folder
- choose whether you want to replace existing files
- add it as a folder action that runs automatically on modification of the source folder
Arguably much slower on the terminal.
Alternative on macOS, that works on all other major OS with similar shortcuts and a similar feature set, just not repeatable:
1. Go to source folder (shift-cmd-G)
2. Filter (cmd-shift-F)
3. Copy (cmd-A, cmd-C)
4. Go to target folder (shift-cmd-G)
5. Paste (cmd-V)
Do you have any sources I can read though? I always find it fascinating when our perceptions are so off like this.
Plus I think there's a nuance to what you're saying:
UX is not just about making the best channel surfing interface, which is essentially what phones/tablets are. We need UIs that are capable of rich interaction and expression of ideas, creation, etc.
Walking around and thinking out loud with the computer.
And as for third party solutions, you have watchGPT for Apple Watch with voice commands and support for adding it as a watch complication.
Cool demo, I suppose, but nobody is going to buy this as anything other than a toy.
Another issue where this comes up is high housing costs, which are mostly caused by bad land use laws (and the nearest evil people, landlords, mostly own one or two properties), but people from the New Left era will literally refuse to believe you about this because they can't accept that any bad thing on Earth could not be caused by "corporations".
I'm not arguing that these models hold up against GPT 3.5 and I still use GPT 4 when it matters. But they work and it's more like the difference between Premier League & Division 1, rather than PL & a five-a-side team from Bracknell.
Even a few years ago I could not have imagined this.
Given the pace of work on optimisation and my assumption that the M3 Studio I buy next will probably have 256GB of RAM at much the same power levels as I use now, it seems eminently possible it's a year or two away.
Second, I don't think it will be that long. There are already LLMs as good as GPT-3 running on average laptops and even phones.
In the next couple of years, you'll see:
- Ordinary PCs, tablets, and phones with dedicated AI chips, like TPUs - they'll be more tuned specifically for LLMs
- Mathematical and algorithmic optimizations will make existing LLMs faster on the same hardware
- Newer generations of LLMs will get even more useful with fewer parameters
The combination of all of these means that it's not at all unreasonable to expect that today's top-of-the-line LLM will be running locally on your device within just a couple of years.
Of course, LLMs in the cloud will advance even further, so there will always be a tradeoff, and there will always be demand for cloud AI, depending on the application.
I think AI fundamentally favors centralization. Except for narrow tasks and domains, there's no such thing as "enough" intelligence. For general purpose AI, you'll always want the best and most intelligent model available, which means cloud rather than local.
Just to play devils advocate:
If you want something done right, sometimes you have to do it yourself. Employees are sort of a universal UI. But you will always know more about what you want done than your agent, whether it’s human or computer. That’s even before considering the principal agent problem.
If you want something done right, other times you will have to get someone else to do it. You know what you want, but you might not have the skills to do it. I can't represent myself well in court, do a good job of plumbing or cut my own hair, so I would ask for experts to do that for me.
Plus if someone is capable, it's often quicker to delegate than do, and if you are delegating to someone with more time to do the task they can often do a better job. Delegating unambiguously is a skill in itself, as instructing AIs will be.
Currently ChatGPT doesn't know it's bad at math, so it can convert a story problem into an equation better than a human but then mess up the arithmetic or forget a step in the straightforward part.
But if you specifically give ChatGPT access to Mathematica and an appropriate prompt, it can leverage a good math engine to get the right answer nearly every time.
Before long, I don't think that extra step will be necessary. It will know its limits and have dozens of other services that it can delegate to.
- constrained context
- part of a hands-free workflow
People are already used to using their phone or car's nav system to give them directions to an unfamiliar place. But even with such a system it's useful to have a human navigator in the car with you to answer various questions:
- What's my next turn again?
- How long till we get there?
- Are there any rest stops near here?
- What was that restaurant we just passed?
- Is there another route with less traffic?
- List of upcoming directions
- Overall route planning
- Surrounding place data
- Traffic data and alternate route information
The information is contextual and constrained based on a current task. In some cases it might be more desirable to whip out your phone and interact with the map to look up the answers on a screen, but often it won't be worth stopping the car, and so the conversational interface is better.
Cooking assistant is a similar case: you are busy stirring something and checking on the oven -- you don't want to wipe the flour off your hands to pick up your phone and ask how many teaspoons of sugar you need. Again: contextual and constrained info based on a current task, and your hands and eyes -- the instruments of traditional UIs -- are otherwise occupied.
Today, our software interfaces generally have one of two kinds of entity on the other end: humans, or other software. In the near future there will be another type of entity: language models. We need to start thinking of how our APIs will change when they're interacting with an LLM -- e.g. they'll need to be discoverable and self-describing; error states will need to be standardized or explicit with instructions on how to correct; they'll need to be fast enough to fit in a conversational interface; etc. It's arguable that such traits are part of good API design today, but in the future they may be required for the API to function in a landscape of virtual agents.
How does this work on public transit?
No they won't. They're actually a pretty terrible user interface from a design perspective.
Primarily because they provide zero affordances, but also because of speed.
UX is about providing an intuitive understanding of available capabilities at a glance, and allowing you to do things with a single tap that then reflect the new state back to you (confirming the option was selected, confirming the process is now starting).
Where AI is absolutely going to shine is as a helpful assistant in learning/using those interfaces, much as people currently go to Google to ask, "how do I do a hanging indent in Microsoft Word for my Works Cited page"? For one-off things you do infrequently, that's a godsend, don't get me wrong. But it's not going to replace UI, it's going to assist.
And the 99% of your tasks that are repetitive habit will continue to be through traditional UI, because it's so much more efficient. (Not to mention that most of the time you're not in an environment where it's polite or possible to be speaking at all.)
I think what's more likely is that an AI based interface will end up being superior after it has had a chance to observe your personal preferences and approach on a conventional UI.
So both will still be needed, with an AI helping at the low end and high end of experience and the middle being a training zone as it learns you.
There's nothing to infer. The sequence is already short. There are no benefits from AI here.
But you raise a good point, which is that there are occasionally things like 15-step processes that people repeat a bunch of times, that the AI can observe and then take over. So basically useful in programming macros/shortcuts as well. But that still requires the original UI -- it doesn't replace it.
Voice is not really clumsy, compared to finding a device, browsing to an app, remembering the interface etc.
Already when we meet a new app, we (I) often ask someone to show me around or tell me where the feature is that I want. Not any easier than asking my house AI. Harder really.
Hard to underestimate the laziness of humans. I'll get very accustomed to asking my AI to do ordinary things. Already I never poke at the search menu in my TV; I ask Alexa to search for me. So, so much easier. Always available. Never have to spell anything.
Everyone agrees setting timers in the kitchen via voice is great precisely because your hands are occupied. It's a special case. (And often used as the example of the only thing people end up consistently using their voice assistant for.)
And asking an AI where a feature is in an app -- that's exactly what I was describing. The app still has its UX though. But this is exactly the learning assistance I was describing.
And as for searching with Alexa, of course -- but that's just voice dictation instead of typing. Nothing to do with LLM's or interfaces.
And when describing apps - I imagine the AI is an app-free environment, where I just ask those questions of my AI assistant, in lieu of poking at an app at all.
So sure, it will still have buttons, but those buttons are really just preset AI prompts on the backend. You can also just talk to your appliance and nuance your request however you want to.
A TV with a remote whose channel button just prompts "Next channel" but if you want you would just talk to your TV and say "Skip 10 channels" or "make the channel button do (arbitrary behavior)"
The shortcuts will definitely stay, but they will behave closer to "ring bell for service" than "press selection to vend".
When taking a shower, I would like fine control over the water temperature, preferably with a feedback loop regulating the temperature. (Preferably also the regulation changes over the duration of the showering.)
Choosing to read the NY times indeed is only a few taps away, but navigating through and within its list of articles is nowadays done quite fast and intuitively thanks to quite a lot of UI advancements.
My point being, short sequences are a very limited set within a vast UI space.
People go for convenience and speed, oftentimes even if there's some accuracy cost. AI fulfills this preference, especially because it can learn on the go.
That exists, but it’s expensive because of the electronics and mechanics involved. There are so many interfaces with this exact problem.
You also almost certainly don’t want non-deterministic hallucination prone AI controlling physical systems.
If you want the shower to save your temperature preferences and start automatically, there’s no reason to build in a computer capable of running an AI.
But in reality you almost certainly don’t want a system like this because you don’t want an AI accidentally turning on your shower when you’re not home, when you do ok to clean it, or grab a razor, or when your toddler wanders in.
Granted an AI could try to determine intent, but it’s never going to get it 100% right. Which is why for physical systems like this you almost always want a physical button to signal intent.
Also that sounds like an awful lot of computing power for everyday UIs. It also doesn’t solve the non determinism problem.
There’s no way to use fewer actuators, and the control system is already dead simple, and uses one temperature sensor per outlet.
Who knows, AI can come up with simpler or cheaper solutions that did not cross our mind. I would say, time will tell.
The lack of AI isn’t what’s holding back your dream of a temperature controlled shower in every house.
For example, instead of telling the machine something like, say, "increase the left margin by a quarter inch," you'd say something like "I want to create a brochure for this new product idea I just had, and I want the brochure to evoke the difficult-to-describe feeling of a beautiful sunshine. Create 10 brochures like that so I can review them."
This presumes, of course, that the technology continues to improve at the same pace. No one knows if that will happen.
Suggestions to improve workflow sound great. But nullifying hard earned knowledge of an interface... I can't see that helping me.
The shining example in my mind is audio/video/graphics applications, where there are good reasons to routinely switch between different views. Knowing your way around those views (which might be custom, but still static), and being able to navigate through them quickly is very valuable.
What does this have to do with the price of tea in China, or AI for that matter? I agree we should have repairable appliances. I also want better AI.
This is already pretty much gone thanks to manufacturers making it extremely difficult to fix things. No AI required.
So yes, I see a market for bespoke non-AI.
Do we want this?
People plugging weird stuff together like a ai chip from a car into a toaster.
If ai becomes hardware chips it could easily be that language processing will be a chip default feature and the rest is teachable like plugin ai chip level 3 into it, boot it and teach it that it's now a toaster.
But at the end we will have the same toaster in 30 years as we have had for the last 30 years.
Sadly the market goes 100% full steam in the opposite direction.
We live in end of times.
Here is my previous experience https://news.ycombinator.com/item?id=34648167 with it not being able to do basic tasks.
It's all fun and games until the mistakes start having a cost.
Other examples: I resorted to using it to order lists for me or adding quotes and commas to them for SQL inserts and such. Nope - when I look at the row count, it somehow drops values at random.
My experience with GPT-4 has been completely different from what you describe. Example:
Generally feedback along these lines doesn't work.
People who are worried about their job security will cling to the worst AI output quality they can find like a life-preserver, and simply will not listen to advice like yours.
Nobody goes the extra mile to embrace an existential threat.
There really is no going back.
Madness!
Never seen something like this and the new results from openai tells us again that we are not close to any reasonable plateau.
LLM-based chatbots can be extremely attractive to the top 30% literacy users in the developed world. They are not a good universal UI. You still need to provide pathways for the user to follow to get done what they need without forcing them to articulate their requirement.
This is why so many people sit in front of a ChatGPT-like service and say, "what would I use this for?" and never use it again.
If it's really true that half of the population can't functionally express themselves verbally then I'd sure like to know that. Or maybe I've misinterpreted something claimed here, because I'm struggling to find these claims plausible.
In the case of kids, of course, that's true, but just because they can't write.
But if you can (and most people can) just having the option of voice input won't help.
I refrain to take a stance about how much of the population is unable to articulate thoughts in writing, (it's probably not great though) but it's probably going to be comparable with how many can't express themselves verbally as well.
I'm talking here about more complex ideas of course. I'm sure average communication is functional.
If my supposition (Speculation? Stronger than it should assertion?) Is true then just interpreting requests verbally will not help
Right?
Where did you get this idea? I found this article (https://www.uxtigers.com/post/ai-articulation-barrier, is this you?), but it makes a leap from literacy to articulacy that I don't understand. It's not obvious to me why an illiterate person would be "functionally inarticulate" assuming they can speak instead of write.
Also, I'm not certain but I think the author is underestimating the abilities of a person with Level 2 literacy. It doesn't seem correct to say that "level 3 is the first level to represent the ability to truly read and work with text", especially when the whole point of LLMs is that you don't have to read a long static document and understand it, you can have a conversation and ask for something to be rephrased or ask followup questions.
I do however run a company that employs lots of blue collar, non-college-educated people, in manufacturing. And although this is in no way scientific, my experience matches this: most people are much more uncomfortable writing than they are reading. Even with reading, most strongly resist reading documentation unless they have to, and prefer trial and erroring their own gut instinct until they happen to find something that works or they give up. (This is less true of the most highly skilled technicians, such as those who troubleshoot robots and low voltage control systems.) The official statistics on literacy are absolutely not a good indicator of how comfortable people are articulating themselves with the written word, much less reading.
This is generally met with disbelief by most people in tech I talk with about this, because for the most part they have nearly zero interaction with this large portion of the population. From their daily experience, 98%+ people can make effective use of these tools.
But almost nobody in this partially literate population wants to write in an empty text box to ask an AI to do things. They can learn to visually navigate a simple UI, especially if it's well-designed, because they can effectively make decisions about what of several paths to take.
Some others here have brought up voice, and I do agree that voice is a more promising avenue, although I think it'll still take carefully constructed conversational experiences to work well (i.e., free form 'tell it what you want' will still not work).
I personally doubt GPT-5 will be as much of an improvement over GPT-4 as GPT-4 was over GPT-3, but that's fine, I can wait until GPT-6 or 7.
Thanks for the laugh, I needed that.
Throughout history, the ruling elite had always relied on the rest of the population to make their food, do their work, and fight in their wars. This is the first time ever that they will no longer have any need for anyone else. Maybe climate change will conveniently do the culling for them...
Of course there's always that option that we end up in a post scarcity space utopia where machine produced wealth is distributed to all, but only deluded idealists can possibly still think that'll ever be a real option as we slink further into techno feudalism with every passing day.
I doubt BCI will ever make sense, on a conceptual level it's still just copying and killing your biological self. AGI will likely solve aging way before that becomes viable.
Like identifying traffic lights in 4th and 5th squares in the second and third row both when there are only four squares?
Sometimes communicating with an intelligent agent is harder than doing things yourself with a good structured user interface where you can communicate your intent clearly.
Until we have mind reading AI that is.
I'd also suggest that one of the early "killer apps" for this may be as an "IVR co-pilot" for actual humans on the phone with customers for their tricky issues.
Can someone please relieve my anxiety?
Let me state the obvious: If the rate of improvement of these AI models continues at the current pace, these AI models will become a superior user interface to every single thing you want to do on your mobile phone, your tablet, your desktop PC, your car, your home, etc.
We live in interesting times.