logoalt Hacker News

JoshTriplett • today at 3:36 PM • 2 replies • view on HN

LLMs love https://tvtropes.org/pmwiki/pmwiki.php/Main/SuspiciouslySpec... . You tell them not to do a thing, they make a point of saying they didn't do the thing.


Replies

WorldMaker • today at 5:30 PM

It's partly a "Don't think of a Pink Elephant" problem. I've worked on several projects where I had to keep telling prompt writers to stop writing negative examples because the more you include the more its "attention" to them is all it has. Like telling a toddler not to do something and being surprised that is now all they can think about and they want to keep doing it. These prompt writers kept getting surprised that I'd delete all their negative examples and harshly worded "Don't do X" and "Never Y" and "NO: Z" sections they spend so much time on and got better results with smaller more focused positive example only prompts.

➕ show 1 reply
orwin • today at 5:24 PM

Huge issue in slop comments.

And btw, if you have slop comments in your PR, you'll get a review from an agent (my company pay for it). I won't bother to read if you didn't bother either.

➕ show 1 reply