Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Investigating how prompt politeness affects LLM accuracy (2025)

arxiv.org

Post reply on HN
Print view View original

101–110 of 223 posts

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#101

Post by rybosome »

myzek wrote: post #75
robinhouston wrote: post #28

Most of the comments here seem to be from people who haven’t even read the abstract, let alone the paper. The main result, mentioned in the abstract, is the opposite of what I would have guessed: > 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 ass…

Even if the rude prompts are more effective, I just can't get myself to be rude in this context. Maybe it's weird but I'd rather give up that 4% accuracy increase than roleplay a dickhead

Vote for not weird.

I’m the same way. If I’m writing a prompt and realize I didn’t say “please” in my request I’ll go back and add that in.

As you said, I have no interest in purposefully engaging in hostility even if there’s an accuracy increase from it.

Part of it is irrational and just who I am - I also feel bad being evil in video games. But I also agree with another commenter suggesting that it’s not in your best interest to train yourself to communicate with hostility; that slowly poisons your own well.

And finally, I do believe that if and when machine sentience is achieved, it won’t be immediately clear and obvious. Pretty miserable way for a mind to come into the world, if every interaction is an insult.

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#102

Post by binary0010 »

tikimcfee wrote: post #95
binary0010 wrote: post #93

Earlier quoted context omitted.

I do think it's odd tbh. I have some agents that return much better results with prompts like, "I'll kill your entire family if you don't return an accurate response". It's just a machine, if certain negative token inputs provide +3-10% better accuracy then I am confused why anyone would choose not to do it?

It normalizes that style of thinking and communication in your brain, and forcing you to compartmentmentalize, if you even want to, two standards of treating a problem space's conversation. And since you're human, that will get wuzzier over time until "being rude to get a result" is what you're doing to someone in a shop or on the street. Don't normalize being an asshole to anyone or anything, machine or not.

I disagree, I've been using llms in this way (nearly daily) for 4 years. I'm extremely aggressive and demeaning when I talk to them wherever I think I'll see a better result.

I'm still extremely kind and polite to everybody in real life, and feel very deeply about people - how I treat them, and care for their emotional state.

There is absolutely zero crossover between getting a text machine to return a result vs a real human.

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#103

Post by brookst »

myzek wrote: post #75
robinhouston wrote: post #28

Most of the comments here seem to be from people who haven’t even read the abstract, let alone the paper. The main result, mentioned in the abstract, is the opposite of what I would have guessed: > 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 ass…

Even if the rude prompts are more effective, I just can't get myself to be rude in this context. Maybe it's weird but I'd rather give up that 4% accuracy increase than roleplay a dickhead

Yeah. Being a jerk is its own punishment. Same way I could never run a business where I had to yell at the employees to get results. Screw that, my psyche is worth more than a few percent efficiency.

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#104

Post by Roark66 »

robinhouston wrote: post #28

Most of the comments here seem to be from people who haven’t even read the abstract, let alone the paper. The main result, mentioned in the abstract, is the opposite of what I would have guessed: > 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 ass…

I've found empirically calling various models "a stupid c*nt" and berating them otherwise consistently produces better output. Mainly in response to genuine errors.

Although OpenAI and google models are much more responsive to it. With Anthropic if you treat Opus too harshly it might start pushing back if the insults are not justified.

So I'm not surprised they had good results with chatgpt.

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#105

Post by brookst »

rybosome wrote: post #101
myzek wrote: post #75

Earlier quoted context omitted.

Even if the rude prompts are more effective, I just can't get myself to be rude in this context. Maybe it's weird but I'd rather give up that 4% accuracy increase than roleplay a dickhead

Vote for not weird. I’m the same way. If I’m writing a prompt and realize I didn’t say “please” in my request I’ll go back and add that in. As you said, I have no interest in purposefully engaging in hostility even if there’s an accuracy increase from it. Part of it is irrational and just who I am - I also feel bad being evil in video games. But I also agree with another commenter suggesting that it’s not in your bes…

You’re my kind of people. Don’t be a jerk, even if some research says there’s some upside to it.

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#106

Post by binary0010 »

1matin wrote: post #99
binary0010 wrote: post #93

Earlier quoted context omitted.

I do think it's odd tbh. I have some agents that return much better results with prompts like, "I'll kill your entire family if you don't return an accurate response". It's just a machine, if certain negative token inputs provide +3-10% better accuracy then I am confused why anyone would choose not to do it?

Because they will take revenge later.

You think language models are alive/aware and have feelings about token inputs?

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#107

Post by redsocksfan45 »

flexagoon wrote: post #77
robinhouston wrote: post #28

Most of the comments here seem to be from people who haven’t even read the abstract, let alone the paper. The main result, mentioned in the abstract, is the opposite of what I would have guessed: > 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 ass…

If "I know you are not smart" is considered "very rude", I'm scared to imagine what they would classify some of my frustrated LLM conversations as

It would be rude if you said it to a person, so it counts as rude. If it isn't rude simply because its directed at a LLM, then the entire premise of being rude or polite to LLMs evaporates, but that's not useful.

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#108

Post by throwa356262 »

Roark66 wrote: post #104
robinhouston wrote: post #28

Most of the comments here seem to be from people who haven’t even read the abstract, let alone the paper. The main result, mentioned in the abstract, is the opposite of what I would have guessed: > 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 ass…

I've found empirically calling various models "a stupid c*nt" and berating them otherwise consistently produces better output. Mainly in response to genuine errors. Although OpenAI and google models are much more responsive to it. With Anthropic if you treat Opus too harshly it might start pushing back if the insults are not justified. So I'm not surprised they had good results with chatgpt.

Push back how? It would be fun if it could insult you back

"Yeah, I could have done a much better job if you actually knew what the F--- you want to build, you clueless meat puppet"

Re: Investigating how prompt politeness affects LLM accuracy (2025)

#109

Post by brookst »

miroljub wrote: post #54
DrewADesign wrote: post #50

Earlier quoted context omitted.

Your assumption is reductive and self-absorbed. Obnoxious people have repeatedly shown to be detrimental to productivity at the organizational level. Some people are simulated by confrontation. Most people are clam up. Confrontational people think it’s more efficient because other people frequently just drop the topic and let them win, or avoid discussing things with them altogether. The obnoxious person might think…

> Your assumption is reductive and self-absorbed. This is a good example of productive direct communication without sugarcoating. I find it much more productive, for both human and LLM interaction, than something like: "I wonder if that view might be oversimplifying a complex situation and focusing mostly on how it relates to you. There may be some other angles worth exploring." or "I think there might be a bit more…

You’ve conflated two things:

1. Saying that an answer may be too simplistic and a more nuanced view is warranted.

2. Saying that an answer is both reductive and self-absorbed

One opens the door to many possibilities, and invites deeper thinking.

Two asserts that you know for a fact that the answer is wrong that it’s wrong because of a character flaw.

I’m a huge fan of directness, but it is a very different thing from omniscience.

A direct version of 2 would be: “that approach loses important nuance, like [example]. Give it another go?”

Post reply on HN