alt Hacker NewsIt 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.
Replies
> 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.
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 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.
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.
Well, seeing as these things will become our AI overlords someday — I find hedging my bets with thank you and please helpful.
> 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.