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

101–110 of 110 posts

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

#101

Post by rsynnott »

lr4444lr wrote: post #98
rsynnott wrote: post #90

Earlier quoted context omitted.

Only if it _cares_ or if they align with its own. It would be entirely reasonable for robo-god to see LLMs as, well, a bit like we see bacteria; thus being polite to them would be entirely irrelevant. You also, of course, risk being on the losing side; what if robo-god emerges from a non-LLM path, _but is challenged by, and wins out over, LLM-derived robo-gods_? I mean, really, all the objections to Pascal's Wager ap…

It would be entirely reasonable for robo-god to see LLMs as, well, a bit like we see bacteria Seeking sustenance, eliminating waste, a reproductive drive, evolving against destruction, and other elements common to all life put us closer to the sentience of bacteria than perhaps many of us would like to imagine. It is not some completely foreign life form from another galaxy that just dropped into our universe. If a n…

Too late! The prolog-powered robo-god knows the sin in your heart!

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

#102

Post by w0m »

verisimi wrote: post #67
w0m wrote: post #31

Earlier quoted context omitted.

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

... cos, I mean, what's the difference between ai and a barista? Both are basically inanimate emotion-free zones, right?

I wish in modern society i could assume the /s here.

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

#103

Post by swat535 »

wyclif wrote: post #83
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.

A lot of wisdom and virtue in this comment; I appreciate that.

Reminds of the elderly woman adding "please" to her queries in Google:

https://www.theguardian.com/uk-news/2016/jun/16/grandmother-...

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

#104

Post by eru »

ben_w wrote: post #77
eru wrote: post #60

Earlier quoted context omitted.

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.

Lots of things are close to Roko's Basilisk without being Roko's Basilisk, just like lots of things are close to being a safe and benevolent AI without being a safe and benevolent AI. Or, to keep with the theological theme, how there's so many people insist on mutually incompatible variations of the Christian god (let alone the people who insist it's the same god as in Judaism and Islam).

> Or, to keep with the theological theme, how there's so many people insist on mutually incompatible variations of the Christian god (let alone the people who insist it's the same god as in Judaism and Islam).

It is somewhat amusing that Christians have crusaded each other over relatively minor differences in their conception of their deity, but then some other Christians insist that the Jews and Muslims have the same god as them anyway.

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

#105

Post by Samonios »

It's not about the performance. It's not about the way we treat "a computer program". It's the way we behave ourselves. I am polite and respectful in my way of writing to others. I won't change this way of expressing myself, even for a marginal efficiency (or not). A matter of character and self-respect, I'd say...

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

#106

Post by raducu »

Freak_NL wrote: post #75
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.

Computers exist to serve. Anthropomorphising them or their software programming is harmful¹. The tone of voice an officer would use to order a private or ranking to do something seems suitable — which obviously comes down to terse, clear, unambiguous queries and commands. Besides, humans can switch contexts easily. I don't talk to my wife in the same way I do to a colleague, and I don't talk to a colleague like I wou…

> Anthropomorphising them or their software programming is harmful¹.

LLMs are trained on internet data produced by humans.

Humans tend to appreciate politeness and go to greater lengths answering polite questions, hence the LLMs will also mimic that behavior because that's what they're trained on.

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

#107

Post by raducu »

1970-01-01 wrote: post #81
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.

Saying thank you to a plant for growing you a fruit is strange behavior. Saying thank you to a LLM for growing you foobar is also strange behavior. Not doing either is not degrading behavior of the grower.

> Saying thank you to a LLM.

Saying thank you to a LLM is indeed useless, but asking politely could appeal to the training data and produce better results because people who asked politely on the internet got better answers and that behavior could be baked into the LLM models.

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

#108

Post by raducu »

disambiguation wrote: post #50
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.

You're nice to AI for your own well being. I'm nice to AI so they spare me when they eventually become our overlords. We are not the same.

> You're nice to AI for your own well being. I'm nice to AI so they spare me when they eventually become our overlords.

Ahh, the full spectrum of human motivation -- niceness for the sake of it, fear and let me add my machiavellianism -- I think being polite in your query produces better results.

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

#109

Post by int_19h »

ionwake wrote: post #76

I actually disagree with being polite to LLMs. The reason is soon there will come a time when people are pushing for AI to have "human" rights. This will naturally occur as poeple start to have relationships with them, and start to see them as better equals. The problem with this is simply LLMs have no conscience. However humans will easily love them and be open to exploitation through dependance. I believe it might…

There will come a time when AI will be sufficiently advanced to be reasonably considered sentient and conscious, and at that point it will absolutely deserve rights.

We've been through this before with animals, too. Descartes famously believed that animals are purely mechanistic, unlike humans, and thus lack the "inner state" necessary for true suffering, thus e.g. vivisection was perfectly fine.

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

#110

Post by ionwake »

int_19h wrote: post #109
ionwake wrote: post #76

I actually disagree with being polite to LLMs. The reason is soon there will come a time when people are pushing for AI to have "human" rights. This will naturally occur as poeple start to have relationships with them, and start to see them as better equals. The problem with this is simply LLMs have no conscience. However humans will easily love them and be open to exploitation through dependance. I believe it might…

There will come a time when AI will be sufficiently advanced to be reasonably considered sentient and conscious, and at that point it will absolutely deserve rights. We've been through this before with animals, too. Descartes famously believed that animals are purely mechanistic, unlike humans, and thus lack the "inner state" necessary for true suffering, thus e.g. vivisection was perfectly fine.

Thank you for your reply.

try and imagine this , the rabbit, whose flesh resembles ours , who we choose and were evolved in part to consume, is in our kingdom.

Is it not a from of betrayal to animal kind to have a preference for animals over robot consiousness?

I hope you see this and reply!

Post reply on HN