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

Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance

arxiv.org

Post reply on HN
Print view View original

51–60 of 110 posts

Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance

#51

Post by ben_w »

deadbabe wrote: post #3

I’m totally against the anthropomorphization of LLMs. These are tools, not sentient beings. Treat them as such. Unlike a power tool, they don’t need respect because they cannot hurt you. LLMs trying to simulate human behavior is like the equivalent of skeuomorphism in UI design.

Unlike a power tool, they speak English. (And Welsh, and…)

Unlike a power tool, their entire interface surface is language.

Unlike a power tool, their training process is to mimic us, in the hope that this does something useful.

Unlike a power tool, they anthropomorphise themselves.

Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance

#52

Post by lupusreal »

causalmodels wrote: post #17

Personally I think people should generally be polite and respectful towards the models. Not because they have feelings, but because cruelty degrades those who practice it.

Yes, if you're communicating with a human language it pays off to reinforce, not undermine, good habits of communication.

Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance

#53

Post by Jeff_Brown »

eru wrote: post #22

> Polite language in human communications often garners more compliance and effectiveness, while rudeness can cause aversion, impacting response quality. We consider that LLMs mirror human communication traits, suggesting they align with human cultural norms. It should be relatively easy to automatically rewrite prompts to exhibit the optimum level of politeness?

I wonder. If the LLM suggests something really dumb, it might be more effective to really let it know that was a dumb idea. That is, the appropriate level of polite ess might depend on context.

Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance

#55

Post by JackFr »

I often find myself saying please and thank you, but the inability of the LLM to pick up tone can be amusing.

After one of the trashed my app in Cursor, and I pounded on my keyboard "WHY WOULD YOU DO THAT!!!" and the model, ignoring my rage and frustration, responded with a list of 4 bullet points explaining why in fact it did make those changes.

Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance

#56

Post by alwa »

SkyPuncher wrote: post #33

When I'm working through a problem with Cursor, I find platitudes go a long way to keeping it grounded. However, when it really refuses to do something then then best way to break the pattern is harsh, stern wording. For example, if it's written code that's mostly correct but needs some tweaking, a platitude will keep it second guessing everything it just wrote. * "That looks great so far, can you tweak XYZ" -> Keeps…

I’ve had the same sense. From your examples, I wonder if part of it is that, while the form is that of a platitude, you’re giving it substantive direction too: giving it an indication of what you’re satisfied with, as distinct from what remains to be done.

Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance

#57

Post by monktastic1 »

w0m wrote: post #31
causalmodels wrote: post #17

Personally I think people should generally be polite and respectful towards the models. Not because they have feelings, but because cruelty degrades those who practice it.

ding ding ding. If you're rude to an LLM, those habits will bleed into your conversations with barista/etc.

I think it depends on the self-awareness of the user. It's easy to slip into the mode of conflating an LLM with a conscious being, but with enough metacognition one can keep them separate. Then, in the same way that walking on concrete doesn't make me more willing to walk on a living creature, neither does my way of speaking to an LLM bleed into human interactions.

That said, I often still enjoy practicing kindness with LLMs, especially when I get frustrated with them.

Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance

#58

Post by brap »

causalmodels wrote: post #17

Personally I think people should generally be polite and respectful towards the models. Not because they have feelings, but because cruelty degrades those who practice it.

When coding with LLMs, they always make these dumb fucking mistakes, or they don't listen to your instructions, or they start changing things you didn't ask it to... it's very easy to slip and become gradually more rude until the conversation completely derails. I find that forcing myself to be polite helps me keep my sanity and keep the conversation productive.

Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance

#59

Post by colinmorelli »

SkyPuncher wrote: post #33

When I'm working through a problem with Cursor, I find platitudes go a long way to keeping it grounded. However, when it really refuses to do something then then best way to break the pattern is harsh, stern wording. For example, if it's written code that's mostly correct but needs some tweaking, a platitude will keep it second guessing everything it just wrote. * "That looks great so far, can you tweak XYZ" -> Keeps…

I wonder if it's the platitude doing that, or the explicit affirmation that _most_ of it looks good, but just XYZ needs tweaking. That intention is explicit in the first message, and potentially implied but unclear in the second.

Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance

#60

Post by eru »

ben_w wrote: post #34
eru wrote: post #25

Earlier quoted context omitted.

Who says that the judgement will be of the form 'you were nicer back then, you get better treatment now'. What if it was the opposite? Or what if it was something totally orthogonal? Pascal's Wager only works if the only god conceivable is one that wants you to believe in her. Instead of one that eg rewards honest atheists, or that just likes left-handers.

Indeed, and this is also one of the points I make to anyone who appears to be in danger of taking Roko's basilisk seriously. There's plenty of other potential AI besides the one in ${insert thought experiment here}.

Roko's Basilisk is slightly cleverer. It gives you an incentive to build exactly Roko's Basilisk, thus making it more likely than the alternatives.

I do agree that it seems that there's still something flawed with Roko's Basilisk. But it's not quite as simple as a vanilla Pascal's Wager.

Post reply on HN