31–40 of 219 posts
Not sure I would lump command line interfaces from circa 1964 with GUIs from 1984 through to the present, all in a single "paradigm". That seems like a stretch.
Also, Uber (and many other mobile apps) wouldn't work as a CLI or desktop GUI, so leaving out mobile is another stretch.
> 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. 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.
SQL is declaritive with a pre-defined syntax and grammar as an interface, where as the AI style of interaction has a natural language interface.
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).
What is really needed is for LLMs to produce some structured markup, that can then be rendered as dynamic documents. Not text.
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.
> 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. This doesn't seem like a whole new paradigm, we already do that. When I hit the "add comment" button below, I'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 i…
> As I mentioned, in command-based interactions, the user issues commands to the computer one at a time, gradually producing the desired result (if the design has sufficient usability to allow people to understand what commands to issue at each step). The computer is fully obedient and does exactly what it’s told. The downside is that low usability often causes users to issue commands that do something different than what the users really want.
Let's say you're creating a new picture from nothing in Photoshop. You will have to build up your image layer by layer, piece by piece, command by command. Generative AI does the same in one stroke.
Something similar holds for your comment: you had to navigate your browser (or app) to the comment section of this article, enter your comment, and click "add comment". With an AI system with good usability you could presumably enter "write the following comment under this article on HN: ...", and have your comment be posted.
The difference lies on the axis of "power of individual commands".
Interesting to bundle both cli/gui under the "command" based interaction paradigm. I'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/gui as a very significant event in the history of computing interfaces.
When you zoom out on the time scale it makes more sense. I think he's got a point. Both CLIs and GUIs are "command based". LLM prompts are more declarative. You describe what you want.
Actually, we can make automomous agents and agentic behavior without LLMs very well, for decades. And we can program them with declarative instructions much more precisely than with natural language.
The thing LLMs seem to do is just give non-experts a lot of the tools to get some basic things done that only experts could do for now. This has to do with the LLM modeling the domain space and reading what experts have said thus far, and allowing a non-expert to kind of handwave and produce results.
Earlier quoted context omitted.
I'm not sure I understand point 1 here. Do you mean that vehicle manufacturers moving away from touchscreens is bad or that they would never have moved to them in the first place if they had properly investigated the idea?
The latter - had they given proper thought to the consequences of moving into touch-screens they would've never gone there. Obviously I'm generalizing and discarding the impact of novelty on sales and marketing.
I thought about interfaces a lot and realizdd that, for most applications, a well-designed GUI and API is essential. For composability, there can be standards developed. LLMs are good for generating instructions in a language, that can be sort of finagled into API instructions. Then they can bring down the requirements to be an expert in a specific GUI or API and might open up more abilities for people.
Well, and for artwork, LLMs can do a lot more. They can give even experts a sort of superhuman access to models that are “smooth” or “fuzzy” rather than with rigid angles. They can write a lot of vapid bullshit text for instance, or make a pretty believable photo effect that works for most people!
Earlier quoted context omitted.
When you zoom out on the time scale it makes more sense. I think he's got a point. Both CLIs and GUIs are "command based". LLM prompts are more declarative. You describe what you want.
Well LLMs are also “command-based”. They are called prompts. In fact they’d just continue the text but were specifically trained by RLHF to be command-following. Actually, we can make automomous agents and agentic behavior without LLMs very well, for decades. And we can program them with declarative instructions much more precisely than with natural language. The thing LLMs seem to do is just give non-experts a lot o…
I think there's a clear difference between a command and a declaration. Prompts are declarative.
FB’s AI head just said LLMs are a fad. 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). What is really needed is for LLMs to produce some structured markup, that can then be rendered as dynamic documents. Not text. As input, natural language is actually inferior to GUIs. I know the debate between command line people and GUI peo…
Any sufficiently advanced software has deep structure and implementation. It isn’t like a poet who can just bullshit some rhymes and make others figure out what they mean.
The computer program expects some definite inputs which it exposes as an API eg a headless CMS via HTTP.
Similar with an organization that can provide this or that servicd or experience.
Therefore given this rigidity, the input has limited options at every step. And a GUI can gracefully model those limitations. A natural language model will make you think there is a lot of choice but really it will boil down to a 2018-era chatbot that gives you menus at every step and asks whether you want A, B or C.