578
Average open source project nowadays (lemmy.zip)
submitted 5 days ago by to c/opensource@lemmy.ml
220 comments fedilink hide all child comments
 

Can't escape AI slop projects from meat proxies man. Every single open source project smells like Claude Code recently. Sad times.

you are viewing a single comment's thread
view the rest of the comments
[–] 0 points 3 days ago (6 children)

How is someone using ai to code a meat proxy? The person guiding the AI is the one with the idea?

I thought meat proxy is someone that uses AI to think , asking it everything and then just regurgitating that instead of coming up with their own thoughts or ideas.

  • permalink
  • fedilink
  • source
  • hideshow 6 child comments
    •
  • [–] 9 points 3 days ago* (4 children)

    How is someone using chef to cook a pizza a customer? The person guiding the chef is the one with the idea?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 1 point 2 days ago (1 child)

    I think a more appropriate analogy would be using a laser cutter to cut pieces of wood from a design you came up with. You used a tool to make something, without the tool you would not have the knowledge to make all the precise cuts by hand.

    Your analogy is comparing ai to a human, when it should be considered as a tool.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 1 point 3 days ago* (last edited 3 days ago)

    "Guide" is doing a lot of heavy lifting there. There's an infinity of difference between asking an AI to make something and using an AI to do the scutt work, looking over the code it made, running IRL tests, asking "why X? Why not Y?", swearing at it like a junior dev, asking it to fix a,b,c then finally getting acceptable code.

    And even with all that - when you set it up correctly - it's still faster than doing it yourself (in certain circumstances).

    It feels more like doing project management / "software engineering" than clacking the keys. It's amazing how different LLMs approach the same task though; I find Codex to be much more by the book than Claude, for example. The Qwen's are like Labradors - eager to please, clumsy, crash into things a lot. GLM and Kimi are different again. Etc.

    You can't let anything just "make me X, make no mistakes". By the time you type in a ticket (with GO/NO GO gates, acceptance criteria etc) you might be looking at 500-1000 lines of text (which is why a re-usable template and procedures are important). You need repeatable procedures, acceptance tests - the lot.

    And so it goes.

  • permalink
  • fedilink
  • source
  • parent