Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI: First New UI Paradigm in 60 Years?

nngroup.com

Post reply on HN
Print view View original

201–210 of 219 posts

Re: AI: First New UI Paradigm in 60 Years?

#201

Post by danielbln »

leroman wrote: post #192

Chat UI/UX is a tool for experts. To drive this point home consider a user prompting "produce a founder agreement document", 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 "legal" 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…

Interesting, I like this sort of wizard approach. Would you share any implementation details? Langchain, presumably?

Re: AI: First New UI Paradigm in 60 Years?

#202

Post by leroman »

danielbln wrote: post #201
leroman wrote: post #192

Chat UI/UX is a tool for experts. To drive this point home consider a user prompting "produce a founder agreement document", 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 "legal" 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…

Interesting, I like this sort of wizard approach. Would you share any implementation details? Langchain, presumably?

Actually, I'm not using Langchain.

I'm now adding "agent" functionality, specifically to enable the AI to do some "research" on the web, at the moment this will also be done without a framework.

So I'm either missing something or I am doing something simple enough that does not require the framework overhead / added value..

Re: AI: First New UI Paradigm in 60 Years?

#203

Post by jncfhnb »

wbobeirne wrote: post #16

> 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…

[flagged]

Re: AI: First New UI Paradigm in 60 Years?

#204

Post by danielbln »

leroman wrote: post #202
danielbln wrote: post #201

Earlier quoted context omitted.

Interesting, I like this sort of wizard approach. Would you share any implementation details? Langchain, presumably?

Actually, I'm not using Langchain. I'm now adding "agent" functionality, specifically to enable the AI to do some "research" on the web, at the moment this will also be done without a framework. So I'm either missing something or I am doing something simple enough that does not require the framework overhead / added value..

I think that's good, langchain is a spaghetti monster and I think you're better off rolling your own, especially now with the baked in functions feature that GPT has'

Re: AI: First New UI Paradigm in 60 Years?

#205

Post by TeMPOraL »

Borealid wrote: post #199
TeMPOraL wrote: post #113

Earlier quoted context omitted.

They may not be a surface directly encoding the "truth" value, but unless we assume that the training data LLMs are trained on are entirely uncorrelated with the truth, there should be a surface that's close enough . I don't think the assumption that LLM training data is random with respect to truth value is reasonable - people don't write random text for no reason at all. Even if the current training corpus was too…

I think this is a misunderstanding of what would be necessary for an LLM to only output truth. Let's imagine there does exist a function for evaluating truth - it takes in a statement and produces whether that statement is "true" (whatever "true" means). Let's also say it does that perfectly. We train the LLM. We keep training it, and training it, and training it, and we eventually get a set of weights where our eval…

Science itself has the same problem. There's literally no reason to be certain that the Sun will rise tomorrow, or that physics will make sense tomorrow, or that the universe will not become filled with whipped cream tomorrow. There is no fundamental reason for such inductions to hold - but we've empirically observe they do, and the more they do, the safer we feel in assuming they'll continue to hold.

This assumption is built into science as its fundamental axiom. And then, all the theories and models we develop, also have "no mathematical guarantee" - we just keep using them to predict outcomes of some tests (designed or otherwise), and compare actual outcomes. As long as they remain identical (within tolerance), we remain confident in those theories.

Same will be the case with LLMs. If we train it and then test it by feeding it data from outside of the training set, for which we know the truth value, and the AI determines that truth value correctly - and then keep repeating it many many times, and the AI passes the test most of the times - then we can slowly gain certainty that it has, in fact, learned a lot, and isn't just guessing.

Re: AI: First New UI Paradigm in 60 Years?

#206

Post by leroman »

danielbln wrote: post #204
leroman wrote: post #202

Earlier quoted context omitted.

Actually, I'm not using Langchain. I'm now adding "agent" functionality, specifically to enable the AI to do some "research" on the web, at the moment this will also be done without a framework. So I'm either missing something or I am doing something simple enough that does not require the framework overhead / added value..

I think that's good, langchain is a spaghetti monster and I think you're better off rolling your own, especially now with the baked in functions feature that GPT has'

I am able to implement complex logic without using this new "functions" feature, I am considering using it with the agent implementation, but might not need to as the new GPT4 version improves on it's JSON handling so that is already plenty robust for my needs..

Re: AI: First New UI Paradigm in 60 Years?

#207

Post by throwuwu »

krm01 wrote: post #44

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). However, the way that AI will contribute to better UI is to remove parts of the Interface. not simply giving it a new form. Let me explain, the ultimate UI is no UI. In a perfect sce…

Having no UI sounds horrible. I don’t want every random desire I have to be satisfied immediately. I’d rather have what I need available at the appropriate time and in a reasonable quantity and have the parameters of that system be easily adjusted. So instead of want pizza = have pizza it would be healthy meal I enjoy shows up predictably at the time I should eat and the meal and time are configurable so I can change them when I’m planning my diet.

Re: AI: First New UI Paradigm in 60 Years?

#208

Post by throwuwu »

leroman wrote: post #206
danielbln wrote: post #204

Earlier quoted context omitted.

I think that's good, langchain is a spaghetti monster and I think you're better off rolling your own, especially now with the baked in functions feature that GPT has'

I am able to implement complex logic without using this new "functions" feature, I am considering using it with the agent implementation, but might not need to as the new GPT4 version improves on it's JSON handling so that is already plenty robust for my needs..

Try out functions in a throw away branch or repo, I wasted a day switching over to them only to find out that they don’t work with my use case at all.

Re: AI: First New UI Paradigm in 60 Years?

#209

Post by throwuwu »

mritchie712 wrote: post #31
DebtDeflation wrote: post #13

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.

Agreed. Also, Uber (and many other mobile apps) wouldn't work as a CLI or desktop GUI, so leaving out mobile is another stretch.

It’s still action/response you have to tap buttons and make choices based on what you see on the screen. The new paradigm would be to tell Uber that you need a ride later after the party and then it figures out when and where to pick you up and what address you’ll be going to.

Re: AI: First New UI Paradigm in 60 Years?

#210

Post by throwuwu »

EGreg wrote: post #37
97-109-107 wrote: post #15

Earlier quoted context omitted.

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.

It seems everyone is in a rush to LLMify their interfaces same as the chatbot rush. Same as the blockchain all the things rush. And so on. 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. Th…

Vapid bullshit is just the default style since it’s the most common format on the web. If you provide a style example, hard data or the right magic words it can produce any type of written content you want.
Post reply on HN