Mirror is an entirely new concept in programming — just supply function signatures and some input-output examples, and AI does the rest.

    • BatmanAoD
      link
      fedilink
      arrow-up
      3
      arrow-down
      1
      ·
      22 days ago

      Doesn’t prolog already “not work half the time”? (Disclaimer: I haven’t used it.)

  • akkajdh999
    link
    fedilink
    arrow-up
    14
    ·
    22 days ago

    So a chatgpt wrapper that compiles a DSL to JavaScript. Ok.

  • thingsiplay@beehaw.org
    link
    fedilink
    arrow-up
    11
    ·
    edit-2
    22 days ago

    I don’t mean this in a toxic way, but this is probably the worst idea I have seen yet with Ai in programming. People should use less Ai, and learn more how to program. It’s better in the long term.

    https://github.com/AZHenley/Mirror

    Is the language and interpretation predictable and exact? If you install a newer version of the Ai, can the exact same code behavior be guaranteed? What’s the benefit over using Ai tools that generate code in a static language, instead leaving it to be interpreted?

    • Reptorian
      link
      fedilink
      arrow-up
      3
      ·
      22 days ago

      People should use less Ai, and learn more how to program

      Yes. Once you know how, you can see pitfalls with AI.

  • jubilationtcornpone@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    9
    ·
    21 days ago

    Most general purpose programming languages nowadays are designed to be easily human readable. But with this, I now have to understand the syntax of another “programming language” in addition to the programming language it outputs. How is this helpful in any way?

    There are already plenty of template generators that can generate boiletplate code with parameters. This seems like a complete waste of time.

    • cakeistheanswer@lemmy.dbzer0.com
      link
      fedilink
      arrow-up
      5
      ·
      21 days ago

      Even as a toy language if I can’t tell what it’s doing beyond interface with an llm prompt… What good is it?

      Consistency and validity of output is essentially impossible to prove, because this has all the accuracy of both humans famously bad at explaining their problems to machines who understand 80% of it.

  • rothaine@beehaw.org
    link
    fedilink
    English
    arrow-up
    7
    ·
    22 days ago
    // Hack the mainframe to skim pennies from ongoing transactions
    async function addMoneyToMyBankAccount(dollarAmount: number): Promise<"success">
    

    Alright let’s go

  • Reptorian
    link
    fedilink
    arrow-up
    7
    ·
    22 days ago

    Interesting, but I never needed AI for coding. Well, twice, and I had to do changes, but would not use AI to generate code.

    • GetOffMyLan
      link
      fedilink
      arrow-up
      1
      ·
      21 days ago

      I use the ai daily at work. But more as an interactive docs and refactoring tool.

  • GetOffMyLan
    link
    fedilink
    arrow-up
    6
    ·
    21 days ago

    The obvious problem is that I would have been quicker to write the function yourself than the examples.

  • KindaABigDyl
    link
    fedilink
    arrow-up
    4
    ·
    edit-2
    22 days ago

    Could I do:

    signature primes_less_than(x: number) -> [number]
    example primes_less_than(2) = []
    example primes_less_than(10) = [ 2, 3, 5, 7 ]
    primes_less_than(10582319112759318014901241439012831231539517)
    

    ?

    I don’t pay for OpenAI, so I can’t try the playground