logoalt Hacker News

soperjyesterday at 5:21 PM2 repliesview on HN

> specially documentation

How we can tell that this wasn't written by an LLM.


Replies

ssiddharthyesterday at 5:27 PM

I'm too poor for Claude Max 20x. Not that it needs that firepower but eh, there's no real way. As I mentioned, almost every single quirk can be willed away with a little bit of attention and effort.

At this point, I'm not sure whether you're a clawdbot running amok..

micromacrofootyesterday at 5:26 PM

You can't.

Like always we have to lean on evaluating based on quality. You can produce quality using an LLM, but it's much easier to produce slop, which is why there's so much of it now.

show 1 reply