@beeoproblem@mastodon.gamedev.place
Post #1602369
2026-03-05 21:33 UTC
@mathew @benjamineskola @zerodogg I've complained about LLMs used for code analysis. Mostly because, if the one used as my day job is representative, they massively suck at it.
Replies (2)
-
@benjamineskola@hachyderm.io 2026-03-05 21:36
@beeoproblem @mathew @zerodogg Yes, precisely. In my experience they produce a lot of output and when you dig through it all there's not actually very much of value to it. And, besides which, if the argument against them is that they're based on plagiarism, that still applies if they're being used for review/analysis and not generation of new code.
-
@mathew@universeodon.com 2026-03-05 21:47
@beeoproblem @benjamineskola @zerodogg Well, yes, and it’s still problematic that corporations are using code contrary to its license to build and ship their analysis tools; but using those tools doesn’t taint an entire project the way code generation does.