Intents: The Endgame for Computing Interfaces?
http200.substack.com
Intents: The Endgame for Computing Interfaces?
1–10 of 21 posts
Re: Intents: The Endgame for Computing Interfaces?
#2Just as we saw a paradigm shift from imperative to declarative interfaces, LLMs have opened the door to new kinds of interfaces.
Intent-driven interfaces are already everywhere - from AI assistants processing raw data, to Arazzo for defining how APIs map to human-scale workflows, to agents capable of handling complex tasks.
While the doomer view is “robots will take all our jobs”, my optimistic take is we finally have a human-centric way of interacting with machines and it’s going to supercharge our abilities
Re: Intents: The Endgame for Computing Interfaces?
#3Since coding with Cursor, I’ve spent a lot of time thinking about how much computing interfaces have changed in such a short period of time. Just as we saw a paradigm shift from imperative to declarative interfaces, LLMs have opened the door to new kinds of interfaces. Intent-driven interfaces are already everywhere - from AI assistants processing raw data, to Arazzo for defining how APIs map to human-scale workflows…
Who is going to pay a thousand times more for a thousand times less?
Re: Intents: The Endgame for Computing Interfaces?
#4Re: Intents: The Endgame for Computing Interfaces?
#5Since coding with Cursor, I’ve spent a lot of time thinking about how much computing interfaces have changed in such a short period of time. Just as we saw a paradigm shift from imperative to declarative interfaces, LLMs have opened the door to new kinds of interfaces. Intent-driven interfaces are already everywhere - from AI assistants processing raw data, to Arazzo for defining how APIs map to human-scale workflows…
If there are two partners and one is a million times faster than the other, are they both necessary? Who is going to pay a thousand times more for a thousand times less?
Re: Intents: The Endgame for Computing Interfaces?
#6Earlier quoted context omitted.
If there are two partners and one is a million times faster than the other, are they both necessary? Who is going to pay a thousand times more for a thousand times less?
If the faster one creates naive, hard to discover bugs, is it really faster? I don't think we understand the long term consequences (or maintenance) of LLM generated code. So far the anecdotal results haven't been great.
Re: Intents: The Endgame for Computing Interfaces?
#7Earlier quoted context omitted.
If the faster one creates naive, hard to discover bugs, is it really faster? I don't think we understand the long term consequences (or maintenance) of LLM generated code. So far the anecdotal results haven't been great.
LLMs seem good at replacing off-shore and very Jr. devs. That’s about it so far. We’ll see if they can get over this current stagnation.
They just seem to replace stack overflow.
Re: Intents: The Endgame for Computing Interfaces?
#8The only issue with it that I can think of it the lack of reporting without asking. When I login to a site, I already want to see the most applicable information without having to ask for it. If I exclusively have to start asking a chatbot for basic info, I may miss out on a lot of what I need to know.
Re: Intents: The Endgame for Computing Interfaces?
#9prolog, sql, chatgpt comes to mind
Re: Intents: The Endgame for Computing Interfaces?
#10People are always getting hung up on the "how to make a GUI if variables are immutable??".
It takes a bit of getting used to, but once over the hump, it seems like GUI's are easier.
See typescript, or fabulous, F#, elm, etc...