Hacker News Reader

Comment by jonathanberger | Hacker News Reader

I don't think it's that anyone wants the interface to be chat. I think it's that the underlying technology is inherently words in and words out. It's similar to how devices with capacitive screens are most naturally going to support tapping, dragging, and pinching.

View on HN

It's funny to me that instead of moving existing tech to a word in word out paradigm, people are dropping millions getting the chat to work with the existing paradigm.

Probably inevitable, but seems like a lot of disruption could happen there.

Text based workflows are king

I mean, that's the first adoption phase where you don't start from scratch but keep using the old tech with the bolted on LLMs. It would take some time for devs to build the primitives around the new tech.

My personal hot take is that the product people (engineers too probably) at these companies are just straight up lazy. Yes, a new UI paradigm is hard, but it's been painfully obvious that chat just absolutely sucks. It's also obvious that some DSL-ish thing is possible, something that just does token juggling and the end-user sees some UI behavior.

I know this all sounds abstract. I've been mulling over it for the past year and it's very hard; and LLMs are super janky and inconsistent so it's 100% not trivial. So in some sense I understand why a lazy bottom-of-the-barrel "chat interface" has become the de facto standard.

Can you elaborate? How in the world would I interface with claude other than sending it messages?

For the abstract "you can do anything" product, you want an open ended interface, but if I'm, eg, renting a car, is a free form text box really the way to go? The rental company knows exactly what information they need from me before they'll rent me a car, so a free form text box so the computer can ask me questions one by one vs a traditional form, seems suboptimal.

But we're talking about Claude right? Not some bespoke app powered by AI? The interface cant only be wide enough to rent cars.

> How in the world would I interface with claude other than sending it messages?

The protocol will of course be `text -> text` for the typical LLM (though some new models are structured, as we saw yesterday with Jev). Even so, the user doesn't need to be exposed to the protocol (almost ever). It's not like I'm crafting a POST request to send this form.

There's a lot of room for window dressing, and I look at AI like I look at the touch-screen. It was a fun technical toy until people (mostly Apple) poured in a lot of serious effort into "ok, how do we make this pleasant to use, intuitive, and genuinely useful?"

So ... what?

Dictation? Neuralink thought-to-text?

So what kind of interface would you prefer?

Reply on news.ycombinator.com