Comment on Are LLMs capable of writing *good* code?
Arbiter@lemmy.world 2 months ago
No LLM is trust worthy.
Unless you understand the code and can double check what it’s doing I wouldn’t risk running it.
And if you do understand it any benefit of time saved is likely going to be offset by debugging and verifying what it actually does.
FlorianSimon@sh.itjust.works 2 months ago
Since reviewing code is much harder than checking code you wrote, relying on LLMs too heavily is just plain dangerous, and a bad practice, especially if you’re working with specific technologies with lots of footguns (cf C or C++). The amount of crazy and hard to detect bad things you can write in C++ is insane. You won’t catch CVE-material by just reading the output ChatGPT or Copilot spits out.
And there’s lots of sectors like aerospace, medical where that untrustworthiness is completely unacceptable.