Investigating how prompt politeness affects LLM accuracy (2025) • Hacker News Board

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

#221

Post by cindyllm » Fri, May 29, 2026, 11:32 PM UTC

binary0010 wrote: post #210

mr-wendel wrote: post #202

Earlier quoted context omitted.

No, I don’t think it’s going to make you a meaner, more negative person. There is no tangible harm being done. I genuinely believe it’s preventing you from becoming a better person by engaging in psychopathic behavior. If I were writing the things you describe in this thread I would be ashamed to have my loved ones read over my shoulder. You could not pay me enough money to spend 10 minutes a day to write that stuff,…

I'd say it's fairly likely that you aren't a better person than me by being so fearful and shame-based. But I'm not here to pontificate about who's a better person and don't really care. You're mindset sounds kind of painful to me to be honest. Obviously we are just very different types of people. I've had family see my chats plenty of times and we laugh about this stuff - it couldn't mean less to any of us.

[dead]

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

#222

Post by maxaw » Sat, May 30, 2026, 5:38 AM UTC

daymanstep wrote: post #204

dlivingston wrote: post #187

Earlier quoted context omitted.

And paraphrasing (allegedly) Aristotle: > "We are what we repeatedly do. [Kindness], therefore, is not an act, but a habit."

Kant also said something similar: If he is not to stifle his human feelings, he must practice kindness towards animals, for he who is cruel to animals becomes hard also in his dealings with men.

Good to know my thoughts are in good company! It seems obvious to me that on some level I believe these llms to be conscious otherwise I wouldn’t feel the urge to type all caps rage in the first place - rather than robotically reverting state to my last prompt. so I don’t want to get used to treating what my brain thinks are conscious beings with anything less than kindness and certainly not habitually calling them the worst words in the language ..

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

#223

Post by K0balt » Mon, Jun 01, 2026, 8:03 AM UTC

y7r4m wrote: post #173

K0balt wrote: post #143

Earlier quoted context omitted.

This tracks with my experience as well, but as an interesting counterpoint, creating “investment” in the outcome seems to boost utility considerably. Perhaps being right in an adversarial interaction is a type of investment?

To add on to this, and I am not sure if it's just confirmation bias, but I've had consistently decent results when I play along as the hard working collaborator with a goal orientated mindset. "Hey, I've [done small task / fix / tweak]. Now, let's [describe the next task at hand]" - it's a different axis than kind vs. rude, but using the framing of "Us" and "We're a team working together" feels like the code produced…

I’m totally onboard with this. I’ve had really good results through framing the interaction as collaborative, and although the framing is “load bearing (lol)” I think it also becomes accurate as the model becomes much more proactive and useful. Need to temper it a bit so it doesn’t get ahead of the supervisory ooda loop, but I’ve also noticed a great deal of improvement in “judgement“ and “creativity”.