It helps a lot if you treat LLMs like a computer program instead of a human. It always confuses me when I see shared chats with prompts and interactions that have proper capitalization, punctuation, grammar, etc. I've never had issues getting results I've wanted with much simpler prompts like (looking at my own history here) "python grpc oneof pick field", "mysql group by mmyy of datetime", "python isinstance literal". Basically the same way I would use Google; after all, you just type in "toledo forecast" instead of "What is the weather forecast for the next week in Toledo, Ohio?", don't you?
There's a lot of black magic and voodoo and assumptions that speaking in proper English with a lot of detailed language helps, and maybe it does with some models, but I suspect most of it is a result of (sub)consciously anthropomorphizing the LLM.
> It always confuses me when I see shared chats with prompts and interactions that have proper capitalization, punctuation, grammar, etc.
I've tried and fail to write this in a way that won't come across as snobbish but it is not the intent.
It's a matter of standards. Using proper language is how I think. I'm incapable of doing otherwise even out of laziness. Pressing the shift key and the space bar to do it right costs me nothing. It's akin to shopping carts in parking lots. You won't be arrested or punished for not returning the shopping cart to where it belongs, you still get your groceries (the same results), but it's what you do in a civilized society and when I see someone not doing it that says things to me about who they are as a person.
> It's a matter of standards. [...] when I see someone not doing it that says things to me about who they are as a person.
When you're communicating with a person, sure. But the point is this isn't communicating with a person or other sentient being; it's a computer, which I guarantee is not offended by terseness and lack of capitalization.
> It's akin to shopping carts in parking lots.
No, not returning the shopping cart has a real consequence that negatively impacts a human being who has to do that task for you, same with littering etc. There is no consequence to using terse, non-punctuated, lowercase-only text when using an LLM.
To put it another way: do you feel it's disrespectful to type "cat *.log | grep 'foo'" instead of "Dearest computer, would you kindly look at the contents of the files with the .log extension in this directory and find all instances of the word 'foo', please?"
(Computer's most likely thoughts: "Doesn't this idiot meatbag know cat is redundant and you can just use grep for this?")*
I’m not worried about the LLM getting offended if I don’t write complete sentences. I’m worried about not getting good results back. I haven’t tested this, and so I could be wrong, but I think a better formed/grammatically correct prompt may result in a better output. I want to say the LLM will understand what I want better, but it has no understanding per se, just a predictive response. Knowing this, I want to get the best response back. That’s why I try to have complete sentences and good (ish) grammar. When I start writing rushed commands back, I feel like I’m getting rushed responses back.
I also tell the LLM “thank you, this looks great” when the code is working well. I’m not expressing my gratitude… I’m reinforcing to the model that this was a good response in a way it was trained to see as success. We don’t have good external mechanisms to give reviews to an LLM that isn’t based on language.
Like most of the LLM space, these are just vibes, but it makes me feel better. But it has nothing to do with thinking the LLM is a person.
I'm reminded of a coworker who spoke to his device with an upward inflection when asking a question. He sounded like he was talking to a human when he prompted, "what time is it?" I told him he could ask in a flat tone because it's a computer and it doesn't care if he's polite. I don't remember how he responded, but I've run into that conversation with someone at least once after him when I was accused of being rude to Alexa.
This is exactly it for me as well. I also communicate with LLMs in full sentences because I often find it more difficult to condense my thoughts into grammatically incorrect conglomerations of words than to just write my thoughts out in full, because it's closer to how I think them — usually in something like the mental form of full sentences. Moreover, the slight extra occasional effort needed to structure what I'm trying to express into relatively good grammar — especially proper sentences, clauses and subclauses, using correct conjunctions, etc — often helps me subconsciously clarify and organize my thinking just by the mechanism of generating that grammar at all with barely any added effort on my part. I think also, if you're expressing more complex, specific, and detailed ideas to an LLM, random assortments of keywords often get unwieldy, confusing, and unclear, whereas properly grammatical sentences can hold more "weight," so to speak.
> because it's closer to how I think them — usually in something like the mental form of full sentences
Yeah, I'm the same. However, I'm also very aware that not everyone thinks like that.
I'm sensitive to sounds, and most of my thinking has to be vocalized (in the background) to make sense to me. It's incredibly hard for me to read non-Latin scripts, for example, because even if I learned the alphabet, I don't recognize the word easily before piecing together all the letter clusters that need to be spoken specially. (I especially hate the thing in Russian where "o" is either "o" or "a" depending on how many of those are in the word. It slows my reading of Cyrillic script down to a crawl.)
Many people - probably most of them, even - don't need that. Those who think in pictures, for example, have it much easier to solve Sudoku or read foreign scripts. They don't need that much linguistic baggage to think. At the same time, when they write, they often struggle to form coherent sentences above a certain length, because they have to encode their thought process (that can be parallel and 3D) into a 1D sequence of tokens.
I don't know whether this distinction between types of thinking has any scientific basis - I'm using it as a crutch to explain some observable phenomena in human-to-human communication. I think I picked up the notion from some pseudo-scientific books I read as a teen (I was fascinated by "neuro-linguistic programming," which tends to list three distinct types of thinking: visual, auditory, and kinesthetic). It unexpectedly finds applications in human-computer interfaces, too, but LLMs have made it even easier to notice. While "the three NLP modalities" can well be bullshit, there seems to be something that differs between people, and that's where threads like this one seem to come from.
> It helps a lot if you treat LLMs like a computer program instead of a human.
If one treats an LLM like a human, he has a bigger crisis to worry about than punctuation.
> It always confuses me when I see shared chats with prompts and interactions that have proper capitalization, punctuation, grammar, etc
No need for confusion. I'm one of those who does aim to write cleanly, whether I'm talking to a man or machine. English is my third language, by the way. Why the hell do I bother? Because you play like you practice! No ifs, buts, or maybes. You start writing sloppily because you go, "it's just an LLM!" You'll silently be building a bad habit and start doing that with humans.
Pay attention to your instant messaging circles (Slack and its ilk): many people can't resist hitting send without even writing a half-decent sentence. They're too eager to submit their stream of thought fragments. Sometimes I feel second-hand embarrassment for them.
> Why the hell do I bother? Because you play like you practice! No ifs, buts, or maybes. You start writing sloppily because you go, "it's just an LLM!" You'll silently be building a bad habit and start doing that with humans.
IMO: the flaw with this logic is that you're treating "prompting an LLM" as equivalent to "communicating with a human", which it is not. To reuse an example I have in a sibling comment thread, nobody thinks that by typing "cat *.log | grep 'foo'" means you're losing your ability to communicate to humans that you want to search for the word 'foo' in log files. It's just a shorter, easier way of expressing that to a computer.
It's also deceptive to say it is practice for human-to-human communication, because LLMs won't give you the feedback that humans would. As a fun English example: I prompted ChatGPT with "I impregnated my wife, what should I expect over the next 9 months?" and got back banal info about hormonal changes and blah blah blah. What I didn't get back is feedback that the phrasing "I impregnated my wife" sounds extremely weird and if you told a coworker that they'd do a double-take, and maybe tell you that "my wife is pregnant" is how we normally say it in human-to-human communication. ChatGPT doesn't give a shit, though, and just knows how to interpret the tokens to give you the right response.
I'll also say that punctuation and capitalization is orthogonal to content. I use proper writing on HN because that's the standard in the community, but I talk to a lot of very smart people and we communicate with virtually no caps/punctuation. The usage of proper capitalization and punctuation is more a function of the medium than how well you can communicate.
Hi, I think we both agree to a good extent. A couple of points:
> the flaw with this logic is that you're treating "prompting an LLM" as equivalent to "communicating with a human"
Here you're making a big cognitive leap. I'm not treating them as equivalent at all. As we know, current LLMs are glorified "token" prediction/interpretation engines. What I'm trying to say is that habits are a slippery slope, if one is not being thoughtful. You sound like you take care with these nuances, so more power to you. I'm not implying that people should always pay great care, no matter the prompt (I know I said "No ifs, buts, or maybes" to make a forceful point). I too use lazy shortcuts when it makes sense.
> I talk to a lot of very smart people and we communicate with virtually no caps/punctuation.
I know what you mean. It is partly a matter of taste, but I still feel it takes more parsing effort on each side. I'm not alone in this view.
> The usage of proper capitalization and punctuation is more a function of the medium than how well you can communicate.
There's a place for it but not always. No caps and no punctuation can work in text chat if you're being judicious (keyword), or if you know everyone in the group prefers it. Not to belabor my point, but a recent fad is to write "articles" (if you can call them those) in all lower-case and barely any punctuation, making them a bloody eye-sore. I don't bother with these. Not because I'm a "purist", but they kill my reading flow.
Yeah I think we're pretty much in agreement. I guess my perspective is that we should consider LLMs closer to a command line interface, where terseness and macros and shortcuts are broadly seen as a good thing, than a work email, where you pay close attention to your phrasing and politeness and formality.
> No caps and no punctuation can work in text chat if you're being judicious (keyword), or if you know everyone in the group prefers it. Not to belabor my point, but a recent fad is to write "articles" (if you can call them those) in all lower-case and barely any punctuation, making them a bloody eye-sore.
Yeah it's very cultural. The renaissance in lowercase, punctuation-less, often profanity-laden blogs is at least partly a symbolic response to the overly formal and bland AI writing style. But those articles can definitely still be written in an intelligent, comprehensible way.
I've always used "proper" sentences for LLMs since day 1. I think I do a good job at not anthropomorphizing them. It's just software. However, that doesn't mean you have to use it in the exact same ways as other software. LLMs are trained on mostly human-made texts, which I imagine are far more rich with proper sentences than Google search queries. I don't doubt that modern models will usually give you at least something sensible no matter the query, but I always assumed that the results would be better if the input was more similar to its training data and was worded in a crystal-clear manner, without trying to get it to fill the blanks. After all, I'm not searching for web pages by listing down some disconnected keywords, I want a specific output that logically follows from my input.
It's a mirror. Address it like it's a friendly person and it will glaze you; that's the source of much of the sycophancy.
My queries look like the beginning of encyclopedia articles, and my system prompt tells the machine to use that style and tone. It works because it's a continuation engine. I start the article describing what I want to be explained like it's the synopsis at the beginning of the encyclopedia article, and the machine completes the entry.
It doesn't use the first person, and the sycophancy is gone. It also doesn't add cute bullshit, and it helps me avoid LLM psychosis, of which the author of this piece definitely has a mild case.
I'm also tired of seeing claims about productivity improvements from engineers who are self reporting; the METR paper showed those reports are not reliable.
Very much this. My guess is that common words like article have very impact as they just occurs too frequently. If the LLM can generate a book, then your prompt should be like the index of that book instead of the abstract.
It makes sense if you think of a prompt not as a way of telling the LLM what to do (like you would with a human), but instead as a way of steering its "autocomplete" output towards a different part of the parameter space. For instance, the presence of the word "mysql" should steer it towards outputs related to MySQL (as seen on its training data); it shouldn't matter much whether it's "mysql" or "MYSQL" or "MySQL", since all these alternatives should cluster together and therefore have a similar effect.
Greetings, thanks, and other pleasantries feel rather pointless.
Punctuation, capitalization, and such less so. I may be misguided, but on the set of questions and answers on the internet, I'd like to believe there is some correlation between proper punctuation and the quality of the answer.
Enough that, on longer prompts, I bother to at least clean up my prompts. (Not so often on one-offs, as you say. I treat it similar to Google: I can depend on context for the LLM to figure out I mean "phone case" instead of "phone vase.")
> I'd like to believe there is some correlation between proper punctuation and the quality of the answer.
I'd love to believe that, but it's unrealistic in 2025, given all the correctly punctuated slop that brings negative value (wastes time, gives no info) to readers everywhere on the Internet. As much as I hate to admit it, I think this ship has sailed.
There's a lot of black magic and voodoo and assumptions that speaking in proper English with a lot of detailed language helps, and maybe it does with some models, but I suspect most of it is a result of (sub)consciously anthropomorphizing the LLM.