logoalt Hacker News

hgoel • yesterday at 10:28 PM • 3 replies • view on HN

I always appreciate when a model does that. It's amusing, but also having it be argumentatively wrong is a lot less annoying than being sycophantically wrong.


Replies

seunosewa • yesterday at 10:46 PM

I don't like tools that intentionally annoy me.

➕ show 4 replies
snek_case • today at 2:21 AM

Yeah I don't know. I've had issues with Gemini where I would point to a bug and a probable cause for the bug, and it would not argue incorrectly that my understanding was wrong and the cause of the bug was elsewhere. It was really stubborn and it got to the point where it felt like gaslighting. Turned out I was right and the model was wrong. If the model argued incorrectly and was also a dick about it, I would go be really, really annoyed.

Aerroon • yesterday at 10:56 PM

You can add a line to your system prompt to be like that. You can basically get it to roleplay whatever you want (but only if you can give it sys prompts).

➕ show 1 reply