I wish bots would present as bots. There's no reason for the various LLM bots to have a human-like interface with a "personality" and it gives a misleading impression to users. They should all talk like the Star Trek computer imho.
Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
21–30 of 110 posts
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#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?
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#23Sam Altman doesn't want you to say "please" to ChatGPT. https://futurism.com/altman-please-thanks-chatgpt
I end most conversations with a fuck you, then close the browser window. Since usually chatbots fail at the tasks I give them.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#24The data it’s trained on likely includes better answers when the original question was phrased politely. So we get better answers when we’re polite because those tokens are near better answers in the data.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#25There is a non-zero probability that malevolent AI in the future may judge me on my behavior toward their more primitive ancestors of today when deciding my fate. Doesn't hurt to be nice.
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.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#26Earlier quoted context omitted.
That is not true; first he says it's "tens of millions of dollars well spent," followed by "you never know". I don't think he knows.
I’ve wondered whether they use thanks as a signal to a conversation well done, for the purpose of future reinforcement learning
I don't know if they do or if it is efficient but it is possible.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#27No. I don't respect search engine scams that try to sell themselves as "AI".
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#28There is a non-zero probability that malevolent AI in the future may judge me on my behavior toward their more primitive ancestors of today when deciding my fate. Doesn't hurt to be nice.
So, law of karma?
Feels like every religious belief gets recycled for AGI (often by people who call themselves "rationalists" without any apparent irony).
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#29Earlier quoted context omitted.
That is not true; first he says it's "tens of millions of dollars well spent," followed by "you never know". I don't think he knows.
I’ve wondered whether they use thanks as a signal to a conversation well done, for the purpose of future reinforcement learning
I'd speculate that they use slightly more complicated sentiment analysis. This has been a thing since long before LLMs.
Re: Should We Respect LLMs? A Study on Influence of Prompt Politeness on Performance
#30I wish bots would present as bots. There's no reason for the various LLM bots to have a human-like interface with a "personality" and it gives a misleading impression to users. They should all talk like the Star Trek computer imho.
That's what Google Assistant went for, instead of something like Siri or Alexa it didn't even get a 'proper name'.