TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

AI: First New UI Paradigm in 60 Years?

291 点作者 ssn将近 2 年前

41 条评论

Animats将近 2 年前
This article isn&#x27;t too helpful.<p>There have been many &quot;UI Paradigms&quot;, but the fancier ones tended to be special purpose. The first one worthy of the name was for train dispatching. That was General Railway Signal&#x27;s NX (eNtry-Exit) system.[1] Introduced in 1936, still in use in the New York subways. With NX, the dispatcher routing an approaching train selected the &quot;entry&quot; track on which the train was approaching. The system would then light up all possible &quot;exit&quot; tracks from the junction. This took into account conflicting routes already set up and trains present in the junction. Only reachable exits lit up. The dispatcher pushed the button for the desired exit. The route setup was then automatic. Switches moved and locked into position, then signals along the route went to clear. All this was fully interlocked; the operator could not request anything unsafe.<p>There were control panels before this, but this was the first system where the UI did more than just show status. It actively advised and helped the operator. The operator set the goal; the system worked out how to achieve it.<p>Another one I encountered was an early computerized fire department dispatching system. Big custom display boards and keyboards. When an alarm came in, it was routed to a dispatcher. Based on location, the system picked the initial resources (trucks, engines, chiefs, and special equipment) to be dispatched. Each dispatcher had a custom keyboard, with one button for each of those resources. The buttons lit up indicating the selected equipment. The dispatcher could add additional equipment with a single button push, if the situation being called in required it. Then they pushed one big button, which set off alarms in fire stations, printed a message on a printer near the fire trucks, and even opened the doors at the fire house. There was a big board at the front of the room which showed the status of everything as colored squares. The fire department people said this cut about 30 seconds off a dispatch, which, in that business, is considered a big win.<p>Both of those are systems which had to work right. Large language models are not even close to being safe to use in such applications. Until LLMs report &quot;don&#x27;t know&quot; instead of hallucinating, they&#x27;re limited to very low risk applications such as advertising and search.<p>Now, the promising feature of LLMs in this direction is the ability to use the context of previous questions and answers. It&#x27;s still query&#x2F;response, but with enough context that the user can gradually make the system converge on a useful result. Such systems are useful for &quot;I don&#x27;t know what I want but I&#x27;ll know it when I see it&quot; problems. This allows using flaky LLMs with human assistance to get a useful result.<p>[1] <a href="https:&#x2F;&#x2F;online.anyflip.com&#x2F;lbes&#x2F;vczg&#x2F;mobile&#x2F;#p=1" rel="nofollow noreferrer">https:&#x2F;&#x2F;online.anyflip.com&#x2F;lbes&#x2F;vczg&#x2F;mobile&#x2F;#p=1</a>
评论 #36397136 未加载
评论 #36397052 未加载
评论 #36400444 未加载
评论 #36396708 未加载
评论 #36401320 未加载
评论 #36401076 未加载
wbobeirne将近 2 年前
&gt; With this new UI paradigm, represented by current generative AI, the user tells the computer the desired result but does not specify how this outcome should be accomplished.<p>This doesn&#x27;t seem like a whole new paradigm, we already do that. When I hit the &quot;add comment&quot; button below, I&#x27;m not specifically instructing the web server how I want my comment inserted into a database (if it even is a database at all.) This is just another abstraction on top of an already very tall layer of abstractions. Whether it&#x27;s AI under the hood, or a million monkeys with a million typewriters, it doesn&#x27;t change my interaction at all.
评论 #36396060 未加载
评论 #36395985 未加载
评论 #36395803 未加载
评论 #36398642 未加载
评论 #36400414 未加载
评论 #36401483 未加载
评论 #36402431 未加载
retrocryptid将近 2 年前
&lt;unpopular-opinion&gt;<p>Bardini&#x27;s book about Doug Engelbart recaps a conversation between Engelbart and Minsky about the nature of natural language interfaces... that took place in the 1960s.<p>AI interfaces taking so long has less to do with the technology (I mean... Zork understood my text sentences well enough to get me around a simulated world) and more to do with what people are comfortable with.<p>Lowey talked about MAYA (Most Advanced Yet Acceptable.) I think it&#x27;s taken this long for people to be okay with the inherent slowness of AI interfaces. We needed a generation or two of users who traded representational efficiency for easy to learn abstractions. And now we can do it again. You can code up a demo app using various LLMs, but it takes HOURS of back and forth to get to the point it takes me (with experience and boilerplate) minutes to get to. But you don&#x27;t need to invest in developing the experience.<p>And I encourage every product manager to build a few apps with AI tools so you&#x27;ll more easily see what you&#x27;re paying me for.<p>&lt;&#x2F;unpopular-opinion&gt;
评论 #36397975 未加载
评论 #36402002 未加载
评论 #36453892 未加载
vsareto将近 2 年前
&gt;And if you’re considering becoming a prompt engineer, don’t count on a long-lasting career.<p>There&#x27;s like this whole class of technical jobs that only follow trends. If you were an en vogue blockchain developer, this is your next target if you want to remain trendy. It&#x27;s hard to care about this happening as the technical debt incurred will be written off -- the company&#x2F;project isn&#x27;t ingrained enough in society to care about the long-term quality.<p>So best of luck, ye prompt engineers. I hope you collect multi-hundred-thousand dollar salaries and retire early.
krm01将近 2 年前
The article fails to grasp the essence of what UI is actually about. I agree that AI is adding a new layer to UI and UX design. In our work [1] we have seen an increase in AI projects or features the last 12 months (for obvious reasons).<p>However, the way that AI will contribute to better UI is to remove parts of the Interface. not simply giving it a new form.<p>Let me explain, the ultimate UI is no UI. In a perfect scenario, you think about something (want pizza) and you have it (eating pizza) as instant as you desire.<p>Obviously this isn’t possible so the goal of Interface design is to find the least amount of things needed to get you from point A to the desired Destination as quickly as possible.<p>Now, with AI, you can start to add a level of predictive Interfaces where you can use AI to remove steps that would normally require users to do something.<p>If you want to design better products with AI, you have to remember that product design is about subtracting things not adding them. AI is a technology that can help with that.<p>[1] <a href="https:&#x2F;&#x2F;fairpixels.pro" rel="nofollow noreferrer">https:&#x2F;&#x2F;fairpixels.pro</a>
评论 #36396256 未加载
评论 #36397141 未加载
评论 #36396492 未加载
评论 #36396527 未加载
评论 #36403499 未加载
评论 #36399689 未加载
评论 #36396954 未加载
评论 #36416759 未加载
kaycebasques将近 2 年前
&gt; With the new AI systems, the user no longer tells the computer what to do. Rather, the user tells the computer what outcome they want.<p>Maybe we can borrow programming paradigm terms here and describe this as Imperative UX versus Declarative UX. Makes me want to dive into SQL or XSLT and try to find more parallels.
评论 #36396020 未加载
评论 #36397170 未加载
DebtDeflation将近 2 年前
Not sure I would lump command line interfaces from circa 1964 with GUIs from 1984 through to the present, all in a single &quot;paradigm&quot;. That seems like a stretch.
评论 #36396962 未加载
评论 #36396007 未加载
评论 #36396004 未加载
d_burfoot将近 2 年前
What strikes me most powerfully when interacting with the LLMs is that, unlike virtually ever other computer system I&#x27;ve ever used, the bots are extremely forgiving of mistakes, disfluencies, typos, and other errors I make when I&#x27;m typing. The bot usually figures out what I mean and tells me what I want to know.
dekhn将近 2 年前
As a demo once, I trained an object detector on some vector art (high quality art, made by a UX designer) that looked like various components of burgers. I also printed the art and mounted it on magnets and used a magnetic dry board; you could put components of a burger on the board, and a real-time NN would classify the various components. I did it mainly as a joke when there was a cheeseburger emoji controversy (people prefer cheese above patty, btw).<p>But when I was watching I realized you could probably combine this with gesture and pose detection and build a little visual language for communicating with computers. It would be wasteful and probably not very efficient, but it was still curious how much object detection enabled building things in the real world and having it input to the computer easily.
评论 #36396900 未加载
andrewstuart将近 2 年前
I would have said ChatGPTs interface is a descendant of Infocomm adventure games which are a descendant of Colossal Cave.<p>When using ChatGPT it certainly evokes the same feeling.<p>Maybe this guy never played adventure.
评论 #36397490 未加载
评论 #36396226 未加载
评论 #36397746 未加载
tobr将近 2 年前
Well, what counts as a “paradigm”? I can’t see any definition of that. If you’d ask 10 people to divide the history of UI into some number of paradigms, you would for sure get 10 different answers. But hey, why not pick the one that makes for a hyperbolic headline. Made me click.
评论 #36396652 未加载
评论 #36396630 未加载
dustingetz将近 2 年前
UI is a high frequency concurrency problem. The “deep rooted usability problems” (like lag, glitches, and clumsiness - general lack of fluency) are due to staffing UI projects with web designers and not concurrency engineers. The fluent conversational AI systems and other movie UIs that folks are imagining up are therefore blocked on the concurrency sub-problem. This is the space we research at Hyperfiddle, we put forth our proposed solution here: <a href="https:&#x2F;&#x2F;github.com&#x2F;hyperfiddle&#x2F;electric">https:&#x2F;&#x2F;github.com&#x2F;hyperfiddle&#x2F;electric</a>
jl6将近 2 年前
Is it a new paradigm, or an old paradigm that finally works?<p>Users have been typing commands into computers for decades, getting responses of varying sophistication with varying degrees of natural language processing. Even the idea of an “AI” chatbot that mimics human writing is decades old.<p>The new thing is that the NLP now has some depth to it.
a1371将近 2 年前
I don&#x27;t really get this. The paradigm has always been there, it has been the technology limitations that have defined the UI so far. Having robots and computers that humans talk to has been a fixture of sci-fi movies. Perhaps the most notable example being 2001: A Space Odyssey which came out 55 years ago.
评论 #36397199 未加载
bambax将近 2 年前
&gt; <i>in command-based interactions, the user issues commands to the computer one at a time, gradually producing the desired result. The computer is fully obedient and does exactly what it’s told.</i><p>&gt; <i>With the new AI systems, the user no longer tells the computer what to do. Rather, the user tells the computer what outcome they want.</i><p>I think that&#x27;s true, and a big part of the AI revolution. Instead of filling endless forms that have subtle controls to guide the user, we could have a simple conversation, like SIRI but that would actually work.<p>At my current client&#x27;s, we&#x27;re working on a big application that has many such forms. Once filled, the forms send the data to a back-end system (SAP). There&#x27;s a team trying to train an LLM so that it can answer questions about the app and about how to fill the forms.<p>But I think the whole point of AI, as regards to this app, is to eventually replace it entirely. Just let end users ask questions and tell the machine what they want, and the machine can build the proper data and send it to SAP.<p>I don&#x27;t think AI is a threat for back-end systems like SAP, at least not yet. But for front-end work, it&#x27;s obvious that it would be infinitely more pleasant -- and possibly, more efficient -- to tell the machine what to do rather than filling forms.
97-109-107将近 2 年前
Two recent events suggest to me that this type of analytical look on interaction modes is commonly underappreciated in the industry. I write this partially from the perspective of a disillusioned student of interaction design.<p>1. Recent news of vehicle manufacturers moving away from touchscreens<p>2. Chatbot gold rush of 2018 where most business were sold chatbots under the guise of cost-saving<p>(edit: formatting)
评论 #36395682 未加载
leroman将近 2 年前
Chat UI&#x2F;UX is a tool for experts. To drive this point home consider a user prompting &quot;produce a founder agreement document&quot;, for which the AI will happily produce -something-. Even thought he user is able to read the document he does not understand the contents in &quot;legal&quot; terms. In contrast if the user would go to an expert lawyer, who would start by asking the user some relevant questions (=domain questions) and put together a prompt tailored to the needs and circumstances of the user in the domain language, with all relevant nuances..<p>I am working to create this experience by augmenting the AI interaction with step-by-step leading questions and interaction UI, similar to how users would interact with a domain expert.<p><a href="https:&#x2F;&#x2F;pth.ai" rel="nofollow noreferrer">https:&#x2F;&#x2F;pth.ai</a> Would love feedback! :)
评论 #36402010 未加载
danielvaughn将近 2 年前
Interesting to bundle both cli&#x2F;gui under the &quot;command&quot; based interaction paradigm. I&#x27;ve never heard it described that way but it does make sense intuitively. Is that a common perception? I think of the development of the mouse&#x2F;gui as a very significant event in the history of computing interfaces.
评论 #36395911 未加载
thih9将近 2 年前
What about voice assistants? These are not as impressive when compared to LLMs, so perhaps wouldn&#x27;t cause a UX shift on their own. But in essence Siri, Alexa, etc also seem to put the user&#x27;s intent first.
评论 #36397661 未加载
评论 #36399710 未加载
Bjorkbat将近 2 年前
I really wouldn’t call GUIs a “command-based paradigm”. Feels much more like they’re digital analogues of tools and objects. Your mouse is a tool, and you use it to interface with objects and things, and through special software it can become a more specialized tool (word processors, spreadsheets, graphic design software, etc). You aren’t issuing commands, you’re manipulating a digital environment with tools.<p>Which is why the notion of conversational AI (or whatever dumb name they came up with for the “third paradigm”) seems kind of alien to me. I mean, I definitely see its utility, but I find it hard to imagine it being as dominant as some are arguing it could be. Any task that involves browsing for information seems like more of an object manipulation task. Any task involving some kind of visual design seems like a tool manipulation task, unless you aren’t too picky about the final result.<p>Ultimately I think conversational UI is best suited not for tasks, but services. Granted, the line between the two can be fuzzy at times. If you’re looking for a website, but you don’t personally know anything about making a website, then that task morphs into a service that someone or something else does.<p>Which I suppose is kind of the other reason why I find the idea kind of alien. I almost never use the computer for services. I use it to browse, to create, to work, all of which entail something more intuitively suited to object or tool manipulation.
评论 #36397437 未加载
kaycebasques将近 2 年前
There&#x27;s something ironic to me about the fact that building AI experiences still requires the first computing paradigm: batch processing. At least, my experience building a retrieval-augmented generation system requires a lot of batch processing.<p>Well, I shouldn&#x27;t say &quot;requires&quot;. I&#x27;m sure you can build them without batch processing. But batch processing definitely felt like the most natural and straightforward way to do it in my experience.
评论 #36397520 未加载
评论 #36398105 未加载
api将近 2 年前
I&#x27;d argue that multi-touch gestural mobile phone and tablet interfaces were different enough from mouse and keyboard to be considered a new paradigm.
评论 #36395755 未加载
travisgriggs将近 2 年前
GPT based UIs inspired by the idea that if you get the right sequence of prompts you’ll get stochastically acceptable results.<p>So now I’m imagining the horror predictions for Word where 90% of the screen was button bars. But the twist is that you type in some text and then click on “prompt” buttons repeatedly hoping to get the document formatting you wanted, probably settling for something that was “close enough” with a shrug.
golemotron将近 2 年前
&gt; Summary: AI is introducing the third user-interface paradigm in computing history, shifting to a new interaction mechanism where users tell the computer what they want, not how to do it — thus reversing the locus of control.<p>Like every query language ever.<p>I&#x27;m not sure the distinction between things we are searching for and things we&#x27;re actively making is as different as the author thinks.
评论 #36395907 未加载
评论 #36395777 未加载
评论 #36395721 未加载
USB3_0将近 2 年前
&gt; With the new AI systems, the user no longer tells the computer what to do. Rather, the user tells the computer what outcome they want. Thus, the third UI paradigm, represented by current generative AI, is intent-based outcome specification.<p>Wow! For the first time ever, I will be able to describe to a trained professional what I want, and they will do it for me! Before today I used to write out the exact arm motions a carpenter would need to carve me a chair, but now I can just ask them for one!<p>This article is stupid. AI will make it easier for computers to interpret human interactions leading to increased efficiency and usability. Just like every other useful tool ever invented. There, I&#x27;ve put more insight into this comment than their article.
layoric将近 2 年前
I built a proof of concept recently that tries to show a generic hybrid of command and intent[0]. The UI generates form representations of API calls the AI agent has decided on making to complete the task (in this case booking a meeting). Some API calls are restricted so only a human can make them, which they do by being presented with a form waiting for them to submit to continue.<p>If the user is vague, the bot will ask questions and try to discover the information it needs. It’s only a proof of concept but I think it’s a pattern I will try to build on , as it can provide a very flexible interface.<p>[0] <a href="https:&#x2F;&#x2F;gptmeetings.netcore.io&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;gptmeetings.netcore.io&#x2F;</a>
isoprophlex将近 2 年前
&quot;intent-based outcome specification&quot;... so, a declarative language such as SQL?
评论 #36397630 未加载
评论 #36396166 未加载
ThomPete将近 2 年前
Here is how I think about it<p>The LLM&#x27;s are infinity app stores. All you need is an LLM and a database plus the ability to speak english and you can replace most features provided by SaaS services today.<p>The GUI becomes a byproduct of the problem you want to solve rather than the gatekeeper to what you can solve.<p><a href="https:&#x2F;&#x2F;twitter.com&#x2F;Hello_World&#x2F;status&#x2F;1660463528984150018?s=20" rel="nofollow noreferrer">https:&#x2F;&#x2F;twitter.com&#x2F;Hello_World&#x2F;status&#x2F;1660463528984150018?s...</a>
评论 #36399166 未加载
marysnovirgin将近 2 年前
The usability of a system is mostly irrelevant. The measure of a good UI is how much money it can get the user to spend, not how intuitively it enables the user to achieve a task.
评论 #36413330 未加载
afavour将近 2 年前
Weren’t voice assistants a new UI paradigm? Also, tellingly, they turned out to not be anywhere near as useful as people hoped. Sometimes new isn’t a good thing.
aqme28将近 2 年前
This is not a new UI paradigm. Virtual assistants have been doing exactly this for years. It&#x27;s just gotten cheap and low-latency enough to be practical.
评论 #36396810 未加载
croes将近 2 年前
&gt;Then Google came along, and anybody could search<p>Then they flooded the search results with ads and now you can search but hardly find.<p>I bet the same will happen with software like ChatGPT.
earthboundkid将近 2 年前
It would be neat if someone could make a good adventure game with an LLM, but they’re too prone to getting argued into just letting you win or whatever.
tasuki将近 2 年前
&gt; Clicking or tapping things on a screen is an intuitive and essential aspect of user interaction that should not be overlooked.<p>I don&#x27;t know, is it? Humanity made do without it for thousands of years.
tin7in将近 2 年前
I agree that chat UI is not the answer. It’s a great start and a very familiar UI but I feel this will default to more traditional UI that shows pre defined actions and buttons depending on the workflow.
trojan13将近 2 年前
I am surprised this article does not even mention multimodal LLMs. Because the more kinds of media the LLM can take as in input and interpret the easier the interaction with it gets.
nologic01将近 2 年前
So many words to describe &quot;declarative programming&quot;
throwoutchatgpt将近 2 年前
ChatGPT and all AI is crap. If we don&#x27;t want to use it, then it will fail to exist and will be nothing but a massive new failure for Microsoft.
EGreg将近 2 年前
FB’s AI head just said LLMs are a fad.<p>I thought about how to use them… I wish they could render an interface (HTML and JS at least, but also produce artifacts like PowerPoints).<p>What is really needed is for LLMs to produce some structured markup, that can then be rendered as dynamic documents. Not text.<p>As input, natural language is actually inferior to GUIs. I know the debate between command line people and GUI people and LLMs would seem like they’d boost the command-line people’s case, but any powerful system would actually benefit from a well designed GUI.
评论 #36396172 未加载
评论 #36396153 未加载
Xen9将近 2 年前
Marvin Minsky, a genius who saw the future.
james-bcn将近 2 年前
That website has a surprisingly boring design. I haven&#x27;t looked at it in years, and was expecting some impressively clean and elegant design. But it looks like a Wordpress site.
评论 #36395733 未加载
评论 #36395578 未加载
评论 #36395619 未加载
评论 #36396360 未加载
评论 #36397040 未加载
评论 #36395644 未加载
评论 #36395599 未加载