[HN Gopher] Intents: The Endgame for Computing Interfaces?
       ___________________________________________________________________
        
       Intents: The Endgame for Computing Interfaces?
        
       Author : dpim
       Score  : 29 points
       Date   : 2024-09-11 15:42 UTC (3 days ago)
        
 (HTM) web link (http200.substack.com)
 (TXT) w3m dump (http200.substack.com)
        
       | dpim wrote:
       | Since 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, 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
        
         | andai wrote:
         | 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?
        
           | candiddevmike wrote:
           | 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.
        
             | cr125rider wrote:
             | 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.
        
               | dartos wrote:
               | Do they?
               | 
               | They just seem to replace stack overflow.
        
               | wpm wrote:
               | Stack Overflow rarely surfaced a solution to your
               | particular problem, but solutions to tangential or
               | otherwise very similar problems. You still had to reason
               | around the posters problem context and try to see if it
               | really matched your own. You still had to have some
               | understanding.
               | 
               | LLMs present a solution as if it is 100% in the context
               | of your problem. You arrive at a solution without being
               | forced to think at all if the solution applies to your
               | problem.
               | 
               | Without being forced to, many will not. I teach
               | programming and I can tell you it is so so obvious when
               | students are just blasting shit from ChatGPT into their
               | submissions without thought.
        
             | mintplant wrote:
             | I've become increasingly frustrated with having to work
             | with other people's AI-"assisted" code. I can _tell_ when I
             | depart from reading sensible human-written code and enter
             | the land of Copilot where all bets are off. Just yesterday
             | I discovered that some environment variables someone had
             | configured on a service weren 't actually doing anything,
             | because the service didn't support being configured via
             | environment variables, let alone those particular ones.
             | It's stuff like that which really gets me about all this:
             | you can no longer assume a coherent theory of mind behind
             | what you're reading. You can no longer trust that because
             | something looks specific and intentional (like environment
             | variable names), that it actually came from reality and not
             | a confabulation. It's breaking the social contract that
             | makes collaboration work.
        
               | jonathanlydall wrote:
               | I don't support stupidly applied AI generated code
               | either, but this isn't a new thing at all, before it was
               | code pasted from Stackoverflow and hammered at until it
               | sort of worked.
        
               | mintplant wrote:
               | Kitbashed SO code at least had some kind of grounding to
               | it. The AI stuff is fully unmoored.
        
       | skratlo wrote:
       | Gave me a good laugh, it's like when they were envisioning flying
       | cars 50 years ago.
        
       | OutOfHere wrote:
       | If I understand, this means to map a chat to a choice of clear
       | API calls. I buy it.
       | 
       | The 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.
        
       | factormeta wrote:
       | >The gradual shift from imperative to declarative interfaces
       | 
       | prolog, sql, chatgpt comes to mind
        
       | FrustratedMonky wrote:
       | Is this basically, how to do GUI's with functional programming.
       | And someone saw the light and it is now the future?
       | 
       | People 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...
        
       | shove wrote:
       | Oh we're playing with fire alright
        
       | david_shi wrote:
       | https://www.paradigm.xyz/2023/06/intents
       | 
       | Check this out
        
       ___________________________________________________________________
       (page generated 2024-09-14 23:01 UTC)