Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Statistically, if it was LLM generated, is it actually more bug dense than human generated code was before this stuff all came out?

This weird take of “an LLM made it, it must be slop and buggy” ignores the reality of how almost all software written by humans was also quite shit before LLM’s came along



Considering the LLM doesn’t pull the code it generates from thin air, I’d argue that it has at least the same bug density with human written code.

However, also considering that LLMs can’t judge the code they have emitted, humans have the advantage here.

Lastly, why we downplay the bugs in the code emitted by AI? Why the lower standards?

- AI generated patch allows access (https://news.ycombinator.com/item?id=49331423)

- Bug in AI scribe creates big problems (https://news.ycombinator.com/item?id=49294441)

As an addenda, human written code is much more maintainable with respect to AI emitted blobs. At least a band of humans can forge that code to a much better shape.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: