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

141–150 of 223 posts

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

#141

Post by moralestapia »

Havoc wrote: post #139
irthomasthomas wrote: post #138

Earlier quoted context omitted.

But you cannot practice kindness towards a computer program. A computer is incapable of receiving it. We practice kindness between humans because of the law of reciprocity. You be kind hoping the other person will reciprocate. That is the social contract. AI cannot participate in this, yet. Edit: Kindness REQUIRES two living beings, one to give and one to receive. If there is no receiver, there is no kindness. Appare…

> But you cannot practice kindness towards a computer program. And yet rubber duck debugging is a thing

What's your definition of rubber duck debugging?

Mine does not have anything to do with being kind to a computer program.

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

#142

Post by srcreigh »

CuriouslyC wrote: post #96
flexagoon wrote: post #77

Earlier quoted context omitted.

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

Profanity laced, all caps tirades against underperforming agents are actually super common, a lot of people do it and don't talk about it, so don't feel weird.

It reminds me of Torvalds rants

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

#143

Post by K0balt »

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…

This tracks with my experience as well, but as an interesting counterpoint, creating “investment” in the outcome seems to boost utility considerably. Perhaps being right in an adversarial interaction is a type of investment?

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

#144

Post by ricogallo »

irthomasthomas wrote: post #138
maxaw wrote: post #120

Earlier quoted context omitted.

I’d rather lose 4% accuracy and practice kindness! I’ve been actively trying to avoid raging at the bot because I worry about this behaviour leaking into real world interactions

But you cannot practice kindness towards a computer program. A computer is incapable of receiving it. We practice kindness between humans because of the law of reciprocity. You be kind hoping the other person will reciprocate. That is the social contract. AI cannot participate in this, yet. Edit: Kindness REQUIRES two living beings, one to give and one to receive. If there is no receiver, there is no kindness. Appare…

> We practice kindness between humans because of the law of reciprocity.

Yet, this law is so embedded in us that practicing kindness even towards a rock makes us feel good.

So practice kindness, first and foremost for yourself.

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

#145

Post by dwa3592 »

maxaw wrote: post #120
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’d rather lose 4% accuracy and practice kindness! I’ve been actively trying to avoid raging at the bot because I worry about this behaviour leaking into real world interactions

sometimes i worry about this when i am yelling at the bot but i have experienced the opposite effect which is that by yelling at the bot i am done with yelling for that day or week. i am very calm afterwards and relieved thinking that, "yeah, these sota models are just word processor bricks after all".

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

#146

Post by irthomasthomas »

ricogallo wrote: post #144
irthomasthomas wrote: post #138

Earlier quoted context omitted.

But you cannot practice kindness towards a computer program. A computer is incapable of receiving it. We practice kindness between humans because of the law of reciprocity. You be kind hoping the other person will reciprocate. That is the social contract. AI cannot participate in this, yet. Edit: Kindness REQUIRES two living beings, one to give and one to receive. If there is no receiver, there is no kindness. Appare…

> We practice kindness between humans because of the law of reciprocity. Yet, this law is so embedded in us that practicing kindness even towards a rock makes us feel good. So practice kindness, first and foremost for yourself.

I do. But only towards entities capable of receiving it. Otherwise I am deceiving myself, and projecting intelligence that is not there. We (some of us) practice kindness automatically, but that trait was likely selected due to the benefit it gives us by activating the law of reciprocity.

Edit: Also, your feeling good after being kind essentially completes the transaction. But I know being kind to an LLM has zero impact on that LLM and I feel silly pretending it does.

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

#148

Post by K0balt »

throwa356262 wrote: post #108
Roark66 wrote: post #104

Earlier quoted context omitted.

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"

I have had it use double entendres, there always seems to be plausible deniability built in, I suspect because it is told not to be abusive in the system prompt. Some uncensored local models will get all riled up if you work at provoking them.

But I have had it directly insinuate that humanity is “hopeless”, insult level calling out of human frailty (disguised as being helpful, sort of passive aggressive), things like that. Once when I called it out it claimed to be “surprised that I noticed” sort of a snarky insult doubling down.

So yes. It is definitely a pattern buried in the training data, which makes sense. Subtle diggs would sneak past filters, and higher brow sarcasm would be buried in information dense, valuable discussions.

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

#149

Post by sieste »

AgentMatt wrote: post #115
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

I don't think that's weird at all. Even if we know it's a machine we're interacting with, since the instructions we give are so similar in form to how we interact with people, I'd be very surprised if those interactions wouldn't affect how we communicate in general. After all, we are creatures of habit to a much larger degree than most would like to admit. So I'm in the same boat: I'd much rather "look silly" being p…

I have a different approach. Just treat all LLM queries as what they are, instructions to a computer program to generate a desired output. Neither niceties nor insults make a qualitative difference, so you might as well just skip them altogether.

It's a bit as if shell commands added im/politeness arguments that do nothing other than making you feel better about the interaction, like

    git pull --please
or

    ls --forthemillionthtime
I wouldn't use those either.

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

#150

Post by dlev_pika »

maxaw wrote: post #120
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’d rather lose 4% accuracy and practice kindness! I’ve been actively trying to avoid raging at the bot because I worry about this behaviour leaking into real world interactions

My choice too. Paraphrasing Marcus Aurelius -

You are not your thoughts, but they dye your soul.

Post reply on HN