Comment by jazzyjackson
2 days ago
Right. You don’t review the machine code or the interaction with registers and branch prediction. If the behavior matches the desired outcome what does it matter?
The classic consideration is, this code will need to be maintained, built on top of… but it’s not like that was ever a solved problem, big projects remain fragile and corporate turnover means no one knows the entire stack. So I see the vibe code out there as just another imperfect way to build barely good enough software.
I’ve also written code I built slowly and intentionally as a piece of art, beautiful code I was proud of. Didn’t make me any money :)
Ah yeah, the good old "you don't check compiler output" argument.
LLM output isn't compiler output. It's a lot of shitty code that contains duplication, subpar algorithms, bad data access patterns etc. We were complaining about awful software before LLMs. Why is it now absolutely okay to write shitty software just because it's LLMs?
Also: literally no one is talking about "writing software as art". We 're talking about this: "many things (redundant code, duplicate code, overly complex architecture, etc.)"
My point wasn’t that compilers are just as bad as LLMs, but that whether humans or robots are writing code, it’s still going to be Just Good Enough to ship.
How do you know it's "Just Good Enough" to ship? I will repeat: We were complaining about awful software before LLMs. Why is it now absolutely okay to write significantly more shitty software just because it's LLMs?
For example, for all the claims of how LLMs are better than humans, or how you can ship gazillion LoC easily, we've yet to see any significant number of actual good software to come out of this slopathon. Even the frontier labs with unrestricted access to their own models who boasting how they merge 30000 PRs per day [1] ship unbelievable buggy shit. But it's okay because it's LLMs who cares?
[1] https://claude.dev/blog/solving-code-review-at-anthropic/