Hacker News Reader

Comment by bko | Hacker News Reader

I think text is the ultimate interface. A company can just build and maintain very strong internal APIs and punt on the UX component.

For instance, suppose I'm using figma, I want to just screenshot what I want it to look like and it can get me started. Or if I'm using Notion, I want a better search. Nothing necessarily generative, but something like "what was our corporate address". It also replaces help if well integrated.

The ultimate would be build programmable web apps[0], which you can have gmail and then command an LLM to remove buttons, or add other buttons. Why isn't there a button for 'filter unread' front and center? This is super niche but interesting to someone like me.

That being said, I think most AI offerings on apps now are pretty bad and just get in the way. But I think there is potential as an interface to interact with your app

[0] https://mleverything.substack.com/p/programmable-web-apps

View on HN

Text is not the ultimate interface. We have the direct proof: every single classroom and almost every single company where programmers play important roles has whiteboards or blackboards to draw diagrams on.

But now LLMs can read images as well, so I'm still incredibly bull on them.

Text is the ultimate interface for accurate data input, it isn't for brainstorming as you say.

Speech is worse than text, since you can rearrange text but rearranging speech is really difficult.

I'd call text the most versatile interface, but not sold on it being the ultimate. As the old saying goes 'a picture is worth a thousand words' and well crafted guis can allow a user to grok the functionality of an app very quickly.

If you haven't gotten an LLM to write you Google/Firefox/whatever extensions to customize Gmail the rest of the Internet, you're missing out. Someday your programmable web apps will arrive, but making Chrome extensions with ChatGPT is here today.

For AI I'm of the opinion that the best interface is no interface. AI is something to be baked into the functionality of software, quietly working in the back. It's not something the user actually interacts with.

The chat interfaces are, in my opinion infuriating. It feels like talking to the co-worker who knows absolutely everything about the topic at hand, but if you use the wrong terms and phrases he'll pretend that he has no idea what you're talking about.

But isn't that a limitation of the AI, not necessarily how the AI is integrated into the software?

Personally, I don't want AI running around changing things without me asking to do so. I think chat is absolutely the right interface, but I don't like that most companies are adding separate "AI" buttons to use it. Instead, it should be integrated into the existing chat collaboration features. So, in Figma for example, you should just be able to add a comment to a design, tag @figma, and ask it to make changes like you would with a human designer. And the AI should be good enough and have sufficient context to get it right.

They thought the same thing in the 70s. Text is very flexible, so it serves a good "lowest common denominator", but that flexibility comes at the cost of being terrible to use.

Reply on news.ycombinator.com