Show HN: TypeLeap: LLM Powered Reactive Intent UI/UX • Hacker News Board

Re: Show HN: TypeLeap: LLM Powered Reactive Intent UI/UX

#21

Post by indexerror » Sun, Mar 09, 2025, 6:56 AM UTC

dheera wrote: post #19

kevmo314 wrote: post #7

Neat idea. Regarding the performance, I think you could get a lot better performance by training a small classifier model, essentially an embedding model, and using the LLM as the distillation source. This would both be much smaller, addressing your desire for it to run in browser, while also being much more performant, addressing your quantization need. Using the full LLM is a bit overkill and you can extract the co…

I just wish the stupid chatbots on customer service websites would show "Get human" as an option sooner. 99% of time there is a mistake and the bots don't have authority to correct it.

Thats why I go for the nuclear option (the one that requires higest attention, like account cancellation) when presented with a list of options by a bot. More likely to get a person that way.

Re: Show HN: TypeLeap: LLM Powered Reactive Intent UI/UX

#22

Post by indexerror » Sun, Mar 09, 2025, 6:58 AM UTC

lukasb wrote: post #11

F7F7F7 wrote: post #6

This is great. But the vast majority of non-gaming non-terminal-loving-developers human beings want to avoid the keyboard at all costs. They are doing it via trackpads, mousepads, touch screens, etc. Which are all inputs that transcend language or the ability to find meaningful words.

ChatGPT has 400 million weekly users

People are coming to ChatGPT with an intent to type. Its much harder to introduce text-based interface to otherwise click-based interfaces because of the friction. Thats why chatbots often fail to gain adoption, because they are a byproduct of the product team being lazy and not thinking through the UX.

Re: Show HN: TypeLeap: LLM Powered Reactive Intent UI/UX

#23

Post by lukasb » Sun, Mar 09, 2025, 7:24 AM UTC

indexerror wrote: post #22

lukasb wrote: post #11

Earlier quoted context omitted.

ChatGPT has 400 million weekly users

People are coming to ChatGPT with an intent to type. Its much harder to introduce text-based interface to otherwise click-based interfaces because of the friction. Thats why chatbots often fail to gain adoption, because they are a byproduct of the product team being lazy and not thinking through the UX.

I 100% agree that grafting a chatbox on an existing app that wasn't meant for it sucks. (I'm working on an AI app where I set a "no chatbox" constraint, see my profile.)

However, I think a lot of people are willing to type if it will do something useful they can't otherwise accomplish. And: typing gives you user intent, very valuable.

Re: Show HN: TypeLeap: LLM Powered Reactive Intent UI/UX

#24

Post by pona-a » Sun, Mar 09, 2025, 10:09 PM UTC

I think this idea of "generative UI" stems from a genuine confusion about what Spotlight, Alfred, or Chrome Omnibox are: they are a collection of utilities, not an app of themselves.

They work because a designer has put some thought into anticipating what kinds of things users search for – formulae, definitions, maps, flights, timers – and designed tiny, polished experiences for each – important in their own right, but not enough to be standalone apps. The NLP component only acts as a dispatcher, calling the right intent with the right arguments.

If these micro-apps are untested unpolished, and most likely broken, having been created here and there without a human touch, they will likely prove inadequate for the user. And if the user is now forced to debug or extend them with natural language and no understanding/control of the underlying code, allowing the power users to write community plugins will have become preferable to this. Not to mention the latency and unpredictability which defeat the standard quick search model.