alt Hacker NewsFortunately we have LLM's to not produce that crap... wait, those LLM's were trained on the existing crap and produce the same crap... oh no.
Replies
bonoboTP • today at 2:13 PM
They were RL trained on verifiable rewards. It's not purely learning to predict the next token of a human produced stream.
I doubt SOTA models nowadays are going to produce an implementation without any kind of authentication like here, and not tell you about it.
And even if, a later "is this ready for release" will probably surface such obvious issues.
I do not think LLMs are the problem here. Today, they are most likely more competent than whoever set this up.