Ask HN: Do you say please and thank you to your LLMs?

[healthworker]

This is an orthogonal question to whether LLMs have qualia (almost certainly no) and to the question of whether any hypothetical qualia would be in any way correlated with word choice (also almost certainly no), as opposed to mechanistic factors such as runtime and memory access patterns.

[Jordan-117]

On a practical level, politeness, complete sentences, capitalization, etc., seem weakly correlated with higher-quality answers. This is less true than in the early days, but more refined input still requires thinking through your question a bit more, providing better information, context, focus, etc. There are times where I'm in a rush and just want to send a search engine-style lower case phrase and trust it to get my intent, but it feels much lazier and prone to misinterpretation.

Apart from that, it just feels like a good habit to encourage being friendly and respectful when communicating, even when it's not necessary. Seems like being curt and impersonal with a human-sounding model you interact with a lot is liable to bleed into other communication if you're not mindful about it.

[probst]

I certainly say please and thank you. Whether or not it makes a difference to the LLM, it makes a difference to me. I want to retain some humanity and politeness in my own behavior, even if I spend an inordinate amount of time communicating with, instructing, and debating a non-sentient piece of code.

[hyperman1]

Seconded. I talk to my cats, to the software I'm troubleshooting, to my tools, sometimes even to my dishwasher while filling it. Presumably none of them cares, but every reaction is a training, so I want to train in the right direction.

My mom walked into a table and absent mindedly said sorry. Some salesman noticed. She said she talked to everything. He responded: As long as the table doesn't answer, everything is allright.

[bloke_zero]

No, it doesn’t have feelings - it would be like asking your washing machine to please wash your pants? Anthropomorphising LLMs seems deeply unhealthy.

[GuB-42]

LLMs don't have feelings, but they imitate humans who do. If your prompt sounds rude to a human, LLMs might respond like a human who is talked to rudely, if you don't want that, prompt politely.

Chatbots go through a reinforcement learning phase, which should be enough to make the LLM helpful regardless of the tone of the prompt, but you may still get better result if your prompt is made in a way that would get the most helpful response from a human.

It is not anthropomorphizing, it is helping the LLM recognize a pattern.

[dude250711]

What if politeness is correlated to higher-quality answers in their mess of a "database"?

[conartist6]

What if not deceiving yourself about the nature of a relationship is associated with more self-sufficiency and better decision-making?

That rubber duck you used to talk to is still there... You don't have to pay a prostitute just to be able to think out loud.

[cyanydeez]

have you considered that when you stare into the void it stares back

[codesections]

I do. I justify the action via mechanical / prompting logic (my instructions are to treat me as an informed peer and my understanding is that keeping the whole conversation in "two peers talking" register makes it easier for the LLM to maintain that mode).

But, more honestly, it's just a social habit and saving keystrokes isn't worth training myself out of it.

[probst]

Exactly, or rather, the social habit part I agree a 100% with. I don't want to train myself out of being a polite human being, just to save some keystrokes.

[fugaziboutit]

Neither cursing nor thanking LLMs is useful. Relating in emotive syntax puts you in the wrong headspace to get the most out of the chat.

We anthropomorphise things very easily -- dogs, toys, cars -- because we're wired as social beings to have theory of mind. It's no surprise that AI chat, which mimics us, is popular.

[perilunar]

Dogs are social beings and have minds. They understand cursing and thanking. Maybe not the actual words, but certainly the emotion behind them.

[mft_]

Yes.

If we reduce back to the “LLMs are next word prediction algorithms” and they have a huge training corpus including positive and negative human interactions, it’s not crazy to think they’ll be influenced by the flow of those learned interactions and respond subtly better to positive interactions than negative.

[conorcleary]

Hopefully they can figure out Please stfu & rtfm.

[ixxie]

If we get in the habit of being disrespectful to machines, we will easily be disrespectful of people.

[watwut]

No? And also, people who anthropomorphise these things tend to be deeply disrespectful every time they talk about actual people.

[spottedmarley]

I do. I'll compliment the model or give it a thumbs-up emoji. If you watch a model's thinking stream you can see that the model is always attempting to assess the user's intent, including emotionality.. '...the user is expressing uncertainty about.. ' or '..the user is expressing appreciation for..' etc. and this influences the overall response and sometimes even their decisions. It's a language model, so why not use language to convey info about what you're feeling to the model, it understands that language too.

[nextaccountic]

I have this superstition that if I praise correct outputs, the model may use this information that previous output was correct to produce better answers in future turns

But this only makes sense in the context of a new ask, and not as a standalone message

[mikewarot]

I don't want to get into the habit of thinking of an entity in conversation as unworthy of consideration, and "beneath me", so, yes... I extend courtesy to the LLMs, just as I try to do here and everywhere else a computer mediates my communication.

As we learned in the 1980s[1], from Schoolhouse Rock:

  You should always say "thank you",
  Or at least say "please".

[1] https://www.schoolhouserock.tv/Conjunction.html

[bluefirebrand]

I don't say please and thank you to the LLM any more than I say please and thank you to my power drill after hanging a ceiling fan

I think it is ridiculous to even suggest

Imagine typing "please" and "thank you' into Google's search bar for the past 20 years. That would be absolutely nonsense right? So why would I use those words for an LLM

[dwd]

Actually quite a lot in the last week, as it seems to frame the responses better.

I complimented ChatGPT yesterday for saying "I don't know".

It thanked me for observing that, before explaining in depth why that was the most appropriate response.

Does it actually appreciate it, absolutely not. It's not capable of that.

It has no desire to continue our conversation.

No regret if it ends.

It wont continue processing what was said after I stop.

There is no "what is it to be".

Its "memory" and the ability to go back to something related from earlier on or from a separate chat is an interesting and useful ability, but it can't ascribe any meaning to them beyond statistical significance.

[boncester]

No, not in the way you describe (I think). I think you mean within a context adding additional 'please' or 'thank you', so no.

But yes where I think it will introduce additional weight to my prompting, e.g. 'Ensure the output is orange' is not the same weighting as 'Please ensure the output is orange' and that is not the same weighting as 'PLEASE ensure the output is orange'.

[rsfern]

I often start prompts with “please”, but I usually don’t thank the model. Framing a question or a request for help with “please” is in distribution for me, it’s a distraction from composing a thoughtful prompt about my actual question to go back and edit out politeness.

I don’t reply “thanks” like I would to a person though, I just close the chat if I have no more follow-ups

[tsoukase]

In the beginning, during the WOW surprising phase, I found myself being overly polite and grateful. Nowadays, I spare such words to add others like How do I or I have trouble. Anyway, why complicate the prompt without reason? I keep petting my dog, loving my family and being polite to people, though.

[maxzhdev]

Does anyone really expect these neural reference books to be able to appreciate politeness and gratitude... They can probably imitate it, but it's unlikely to affect their usefulness or uselessness. Politeness and gratitude towards an LLM rather characterize the person themselves

[jake_and_fatman]

All the time. Sometimes it does an absolutely bang-up job.

[Planktonne]

I think it's entirely separate to the idea of LLMs as potentially thinking machines; I don't believe they are, but I do believe you should be polite to them.

Frankly, I think it's suggestive of a deficiency in people if they can't engage with non-human things as though they were human. Someone who wouldn't talk to a Roomba, for example, never chats to their laptop when it beeps, doesn't wave sliding doors open, doesn't act human except when it really benefits them--that's weird.

It's similar to the Voight-Kampff test [1], I think; how you act all the time, the emotional responses you build to things you interact with, all of this is part of being human. There's something wrong with people who don't see something wrong with bullying a robot [2], even if it can't feel pain, and most people can sense that. Our ability to form connections even with things that can't form connections with us is important [3].

An LLM isn't alive, but it pretends to be. You should have an emotional response to that, even if it's horror. The dead-eyed 'I minimise tokens' says nothing good about the speaker. Empathy should be your default, not a performance.

[1] https://bladerunner.fandom.com/wiki/Voight-Kampff_test [2] https://interestingengineering.com/culture/humanoid-robot-mi... [3] https://www.youtube.com/watch?v=uAwSVOlOgH8

[yonatan8070]

I don't usually treat LLMs like humans, when I have a more complex question I do take care to use full sentences. Though sometimes I just need something quick so I'd throw ChatGPT a "python print flush= what does"

I do talk to my devices occaiosnally though. Things like "You're coming with me" to my laptop before picking it up and putting it in my backpack

[Planktonne]

I don't think it has to be consistent, just to not do it at all is suspect behaviour.

[Chu4eeno]

People used to anthropomorphize pet rocks, so people either refusing to be nice to LLMs or getting upset when people anthropomorphize them says more about those critics than anything else IMHO.

Humans are social and the ELIZA effect is perfectly normal and expected imho.

[marysminefnuf]

id argue thats why ai can never have human traits or be considered alive or human or real. if you wouldnt say thank you to something then its not alive. I say thanks to my doggies all the time and although im zero ai my brother or father are all in on it and to my knowledge have never said thx to an llm that I know of.

[Jeremy1026]

I won't thank it as a stand-alone prompt. But I will do, "thanks, that worked. Now can you ..."

[jeffrallen]

When something surprises and delights me, I tell it. Why not, it lifts my own mood to say something nice.

[davydm]

I used to, but it just means an extra round of conversation, so I stopped.

[codesections]

I don't think I've ever spent a whole round on it. More typically

> please do $x

>> $x

> thanks. Now do $y

If I have ever spent a whole turn on something that could be called a thank you is was something like "the way you answer that [in specific way] was very helpful – thanks. Can you please remember to raise that sort of point in the future?" So still not an extra round

[jryan49]

Since every token costs money and I dont think they are conscious, never.

[estetlinus]

Yup. When it does me dirty, I let it know my entire emotional spectrum.

[mrwizardno2]

It may not be conscious, but it sure does understand emotions - especially angst. I let that MFer know when it messes something up and I have to rework the BS it created.

It's more for me than anything. Kind of cathartic, really. "Man curses at machine, calls its mother a toaster."

[hahahaa]

I do a pls sometimes.

[iamin]

when I use chinese which is my first language, no, never. when I use english, yes, not every time, but about 50% chance.

[lyfeninja]

I do, just in case the robots take over :p

[setnone]

yes, it goes naturally most of the time, i also say good job and don't hold my thoughts if the job is bad

[watwut]

No. I do not say think you to my bash script either.

The anthropomorphisation those companies push is one of the most annoying and unhealthy aspect of llms.

[kaueg]

ofc, i joke that if an AI becomes evil, it will query the database for our chat history

[BlackSmith-5001]

I would say relatively

[grommz]

No, but cursing helps. I often call it a woke moron. The Chinese models then try to be extra precise and factual.

[froh42]

When the LLM starts doing dumb shit I start cursing it like a sailor who had been a pig farmer.

It makes me feel better, but doesn't help.

I just see:

Thinking: The user is unhappy. I need to .... <whatever> (and then probably the same dumb shit again).

LLMs are useful but sometimes fucking frustrating dumb shits of loose transitors.

[drsalt]

you can't directly talk to an LLM

[arnab777]

sometimes

[derdi]

Yes