• 0 Posts
  • 54 Comments
Joined 8 days ago
cake
Cake day: October 31st, 2026

help-circle
  • “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.








  • You’re jumping into the middle of a conversation where OP delightfully asked if Claude was puppeteering me anally when I asked him if he knew what ethical meant, besides several other bon mots and snide remarks to myself and other posters.

    View the full conversation in context.

    OP has an FuckAI axe to grind (click their post history), not a substantive point to make.

    This is not a serious thread. This is a dogwhistle for the FuckAI crowd.






  • Lol at “pressed”. You’re loud and you’re all over this thread like a rash. I’m taking a shit at the dentist and replying to you. That should tell you how much your posts matter to me. It’s literally up there between getting cavities filled and flushing a turd.

    And yes, I get it. Big words and basic logic confuses you. No wonder you think my replies are AI-generated.

    “If you disagree with me, you must be a machine. Say ad-hominem again!”.

    You’ve gone from “99.99% of Rust projects are slop” to critiquing my writing style and implying I’m a clanker. But still no evidence for anything you’re caviling against. Still no logic. Still no idea about agents.md, Kant or much of anything. Lots of big feelings though. Lots of personal insults and shit talking.

    Oh look - I used 3 in a row. Must be AI gen.

    TTFN.