[graemep]

Is it worth getting worse results for that reason? From the article:

"Contrary to expectations, impolite prompts consistently outperformed polite ones, with accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts. These findings differ from earlier studies that associated rudeness with poorer outcomes, suggesting that newer LLMs may respond differently to tonal variation. "

I am not polite to LLMs because I do not want to anthropomorphise them.

[jcattle]

I guess it's about habit. In the end you are communicating. If I get into the habit of being rude while communicating with a machine, I would be afraid of this habit spilling over to my communication with other humans.

[zahlman]

I don't feel like trying to get information from an LLM is a different kind of "communication" from, say, writing code. And I don't use INTERCAL, so.

[graemep]

What about the risk that talking to a machine as though its human leads to thinking of it has human? That leads down a lot of dangerous paths.

[theanonymousone]

> Is it worth getting worse results for that reason?

> accuracy ranging from 80.8% for Very Polite prompts to 84.8% for Very Rude prompts

I can live with that, for now at least.