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

131–140 of 223 posts

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

#131

Post by binary0010 »

serf wrote: post #116
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'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? then add it to your pre-prompt, no need to practice roleplaying as an asshole.

Well I always just start with practical stuff, unless it appears it's going off rails ona specific kind of way repeatedly. Then I try extreme negative prompts to see if it fixes the issue - which it often does.

I wouldn't say I'm roleplaying an asshole. I'm just using an llm in the best way to get the best accuracy.

It's not like a personal, secret fetish. It's just a system I use as needed.

I don't get why you are so uncomfortable with this? It's just tokens in and out of a language model. I feel absolutely nothing when I'm typing "assholish" words to get the output I need.

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

#132

Post by tikimcfee »

binary0010 wrote: post #126
tikimcfee wrote: post #113

Earlier quoted context omitted.

Then I'll be honest and say that your kindness is likely a façade and I wouldn't trust you if I knew the real you. I'm sorry to say that, and I really don't know who you are at all, but if you're willing to act that way at something that you feel is non-sentient, then all it takes is for someone to convince you that something is non-sentient for you to treat it that way. So, what words does it take for you to conside…

Interesting, so you think the real "me", is the one that interacts with computers? And the "me" that lives in a tiny southern town just to help my 95 year old grandma in her last years at the expense of my economic prospects is a facade. The "me" that helps my aging neighbor when she's sick for no reason is a facade. The "me" that hugs and loves my wife when I get home is a facade. The "me" that brushes my aging dogs…

Yes - the real "you" is the one making all of those choices you just said you made, to help people and pets, or to engage in a form of play - which by definition is not "real" - including your decision to create an outgroup you believe you are allowed to treat in a lesser way.

This is not a game of having done X good things in life and therefore being afforded the right to do Y bad things. You are making a choice to say, "I am allowing myself to treat this thing I believe is lesser than me in a way I willingly acknowledge is bad." That's your thesis. I wholeheartedly disagree with it.

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

#133

Post by burpingtree »

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.

This is a very odd view to me, but seems prevalent here in this thread. I think treating a machine like a human is extremely degrading to humans. A machine should never be treated like it’s anything approaching a human.

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

#134

Post by binary0010 »

tikimcfee wrote: post #132
binary0010 wrote: post #126

Earlier quoted context omitted.

Interesting, so you think the real "me", is the one that interacts with computers? And the "me" that lives in a tiny southern town just to help my 95 year old grandma in her last years at the expense of my economic prospects is a facade. The "me" that helps my aging neighbor when she's sick for no reason is a facade. The "me" that hugs and loves my wife when I get home is a facade. The "me" that brushes my aging dogs…

Yes - the real "you" is the one making all of those choices you just said you made, to help people and pets, or to engage in a form of play - which by definition is not "real" - including your decision to create an outgroup you believe you are allowed to treat in a lesser way. This is not a game of having done X good things in life and therefore being afforded the right to do Y bad things. You are making a choice to…

Oh, you think llms are a sentient' being with feelings. I get your perspective now.

So yeah, I whole heartedly with 100% of my being think llms are just an input/output/processing computer, I don't think they are aware, feeling, sentient beings.

So yeah, putting negative sentences in a processing machine that forces it to return higher accuracy results is something I don't have any feelings about.

I'd never yell at a cat or a dog. I'd never be mean to another person. As those aren't just hardware/software. I'd be fine smashing a rock violently. Or entering a negative text in a language model.

Putting negative tokens in a machine is no different than playing a violent video game to me. It's not about, oh I'm a good person - so I can do bad things. It's just a neutral thing.

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

#135

Post by voakbasda »

binary0010 wrote: post #130
voakbasda wrote: post #123

Earlier quoted context omitted.

If someone can justify abusing a computer, I would not trust them to not make a similar justification to a faceless voice on the internet, particularly in this new era where people are starting to accuse each other of using AI in their communication.

I truly do not believe llms have feelings. I wouldn't even think to justify such a thing. The llm gives a better accuracy to a negative weighted token input, I don't understand how this is so upsetting to people? I'm actually very shocked to see the responses - as everyone I know uses these tactics to get more accuracy, and there's nothing remotely abusive or meaningful to us. Maybe there are more 'ai is sentient' ty…

Where did I imply they have feelings? I am saying that how you act toward a machine is real. As real as your behavior directed toward other humans.

Being an asshole to a machine is still being an asshole.

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

#136

Post by moomin »

Asraelite wrote: post #81
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…

You are conflating obnoxiousness with directness.

That’s mostly a problem for obnoxious people, honestly.

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

#137

Post by binary0010 »

voakbasda wrote: post #135
binary0010 wrote: post #130

Earlier quoted context omitted.

I truly do not believe llms have feelings. I wouldn't even think to justify such a thing. The llm gives a better accuracy to a negative weighted token input, I don't understand how this is so upsetting to people? I'm actually very shocked to see the responses - as everyone I know uses these tactics to get more accuracy, and there's nothing remotely abusive or meaningful to us. Maybe there are more 'ai is sentient' ty…

Where did I imply they have feelings? I am saying that how you act toward a machine is real. As real as your behavior directed toward other humans. Being an asshole to a machine is still being an asshole.

That doesn't make any sense. If a thing has no feelings, and an output makes it more accurate, I cannot for the life of me understand why that would make a person an asshole.

So boxing is violent. And I have chosen to box in my past. Does that mean I'm a violent person now? Even though I go out of my way to deescalate real fights?

I play games as the villain and and mass murder people in the game. Does that mean I'm a violent extremist?

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

#138

Post by irthomasthomas »

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

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.

Apparently some people get a dopamine hit from roleplaying kindness toward inanimate objects. Whatever turns you on, no hang ups here. For me, that dopamine hit is not worth the 4% intelligence tax.

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

#139

Post by Havoc »

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…

> But you cannot practice kindness towards a computer program.

And yet rubber duck debugging is a thing

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

#140

Post by pjdesno »

giraffe_lady wrote: post #124
RugnirViking wrote: post #78

I saw this paper the other day - I feel its result may be because the "polite" prompts they have chosen arent very good at putting the ai in the roleplay-space of a valued colleague, more like a sommelier or a high-end shopkeeper. It disagrees with most other literature on the same topic, which is worth keeping in mind. This one studies gpt4o, an old model now, but a lot of other studies are on even earlier models. "…

> "Can you kindly consider the following problem" not how anyone would actually speak to a valued collegue one considers smart. Man idk, it's not how I talk but there's like 100 million nigerian english speakers, twice that indian, and they have some speech mannerisms that surprise me the first few times. I'm pretty sure I've heard exactly this from a colleague before. Intuition about what a native speaker would do w…

Note that there are a fair number of native speakers of English in Nigeria - more than in all but 3 or 4 US states.

In addition, "non-native" English speakers in India (and Nigeria?) typically study English from the first grade, and in many cases attended elementary schools where English was the language of instruction.

I think the differences between US English and both Indian and Nigerian English have more to do with divergent evolution of the educational systems. British English has a lot of differences, too, but we don't notice it as much unless we run across things like "whilst", probably because there's more media crossover. (if you find yourself reading Thomas the Tank Engine to kids it jumps out at you, though - the entire vocabulary for railroads evolved during a period when US and British English were diverging)

Post reply on HN