Comment on Why you should be polite to AI
MountingSuspicion@reddthat.com 1 week agoI think the issue is the post title. If the title was “role-based prompt engineering” you probably wouldn’t have gotten as many comments and certainly not as many disagreeing. She says she’s going to make a case for using please, and then fails to provide any actual examples of that. Pointing that out isn’t sanctimonious, nor does it mean people are being rude to AI. If you want to make a moral argument for it go ahead, but it seems like she’s attempting to propose a technical argument and then just doesn’t. For what it’s worth, I generally try and leave out superfluous words from prompts, in the same way that googling full sentences was previously less likely to result in a good answer than just key words. AI is not human. It’s a tool. If being rude to it ensured it would stop hallucinating, I don’t think it’d make you a bad person if you were rude to it.
There’s a comment here talking about antisocial behavior in gaming, and imho, if you without hesitation kick a dog in a video game, I’m not sure I’d view you the same way after. Plenty of people talk about how they struggle to do evil play throughs because they don’t like using rude options for npcs. Not saying please to AI doesn’t make you a psychopath.
sabreW4K3@lazysoci.al 1 week ago
I don’t editorilise titles. However they’re presented is how I post them. As for people being shit. There’s a reason I post to beehaw and stay away from LW where possible. Every once in a while standards slip here and it results in a new sticky.
As for the argument she’s making. Yes she could’ve made it in a more long form format and provided data. But it’s a short, the emphasis, being that it’s beehaw, was on discussion in good conscience.
I think AI, like front row/customer facing staff deserve to be treated as we would like to be.
MountingSuspicion@reddthat.com 1 week ago
Regarding the post title, I didn’t mean to indicate it being your decision, just that the title in general feels misleading, seeing as no argument is presented and it purports to be about “why” you should do something.
I don’t really know a lot about the difference between instances, so I can’t really opine on that. From what I’m seeing, it does look as though people are having a discussion, they just don’t seem to agree with the idea as presented.
I’m not saying it has to be longer format. I’m saying no argument is made. She could have gave ai the same prompt but with a please and compared the results. I have done so below. She could have used the irrelevant middle section to just display screenshots.
It’s fine if you think people should be polite to ai. I think that’s great, but if you feel that way regardless of effect on response quality then this video doesn’t really make that point either. I think a post saying that and offering your personal opinions might’ve prompted more discussion on that topic rather than just disagreement with a video that doesn’t make that argument.
Here are two prompt comparisons. There is imho no difference in quality when saying please. The same results can be seen regardless of prompt length or how polite I was, I just chose short examples that could have been used in a video if they actually illustrated her point.
List five animals
Here are five animals:
List five animals please
Here are five animals:
Create a limerick about being polite
There once was a person so fine, Whose manners were truly divine. They’d say “please” with a grin, And “thank you” within, And their politeness was truly sublime.
Create a limerick about being polite please
There once was a person so bright, Whose politeness was a delight. They’d hold doors with care, And listen with flair, And their kindness was always in sight.