logoalt Hacker News

frodowtf2 • last Friday at 6:01 AM • 2 replies • view on HN

> In both cases the code will be crap, as no model I've seen produces good code.

I'm wondering if you have actually used claude code because results are not so catastrophic as you describe them.

Replies

rstuart4133 • last Friday at 6:27 AM

I used LLMs to write what seems like far too many lines of code now. This is an example Opus 4.6 running at maximum wrote in C:

    if (foo == NULL) {
       log_the_error(...);
       goto END;
    }
    END:
    free(foo);
If you don't know C, in older versions that can be a catastrophic failure. (The issue is so serious in modern C `free(NULL)` is a no-op.) If it's difficult to get a `FOO == NULL` without extensive mocking (this is often the case) most programmers won't do it, so it won't be caught by unit tests. The LLMs almost never get unit test coverage up high enough to catch issues like this without heavy prompting.

But that's the least of it. The models (all of them) are absolutely hopeless at DRY'ing out the code, and when they do turn it into spaghetti because they seem almost oblivious to isolation boundaries, even when they are spelt out to them.

None of this is a problem if you are vibe coding, but you can only do that when you're targeting a pretty low quality level. That's entirely appropriate in some cases of course, but when it isn't you need heavy reviews from skilled programmers. No senior engineer is going to stomach the repeated stretches of almost the "same but not quite" code they churn out.

You don't have to take my word for it. Try asking Google "do llm's produce verbose code".

➕ show 2 replies
taormina • last Friday at 3:22 PM

Having used Claude Code extensively, catastrophic is a perfect word to describe it.