i hate writing prompts for AI
Had a workshop-like thing about LLMs at work a few days ago. Made me think of one thing I really couldnāt stand about actually using AI back in 2023 and that still hasnāt changed nowadays from what I can tell: How much it is like trying to train someone in the task in the shortest text possible.
As if I had just about 30 seconds to tell someone what to do and thereās lots of caveats I need to include so they arenāt wasting both of our times and making a mistake. Iāll have to give so much context and restraints around the actual topic or code, then specify how I want the output to be. Itās so much work just to not do the thing myself? I wanna keep it as short as possible because I donāt wanna write a novel upfront for something I used to be able to search in a search engine, for example, or when it takes less effort to just do it myself then. It feels like a waste of cognitive resources. I am not thinking about the problem or text Iām about to write, instead I am being asked to think like the machine so I can craft a prompt that doesnāt make it shit the bed.
Maybe I think this way because this type of conversation that AI is mimicking seems to be more exhausting to me in general, but having to include shit like āBe concise.ā and other wishes around its tone or choice of words and size of output is turning me off from using it, even if all other issues around it would be addressed. Literally in any other software, I pull the respective lever (clicking a button, moving a slider, dragging and droppingā¦) and Iām in control. I can just generate what I need. Meanwhile here, I have to give up control and plead with it and hope it follows the instructions so the first result doesnāt sound like an extra wordy (and incorrect) Quora reply.
The first reply usually made me realize it found the exact caveat or restriction I forgot to mention because itās common sense to me, so Iām forced to iterate again. And again. And then thereās a mistake. So again. And again. The way Iāll have to continue bossing around this trainee in everything, master of none pisses me off.
The novelty of bot conversations simply has worn off for me quite a while ago, I fear. Iāll say it: Iām probably not a āteam playerā and I work better alone. Always hated group projects. Maybe thatās why I donāt care to ācollaborateā with AI? Iāve had many situations in the past when just doing it myself would have been quicker and more fruitful than hashing it out with another person, and AI is even worse - at least other people have common sense, know what the topic is and read the room (usually). Iām also admittedly a very impatient person, so when I see text models flap their virtual gums over a simple request I get bored halfway through.
And yeah I know, ask AI bros and Iām the problem, weāre all just too stupid to use it, yada yada. I donāt mind, maybe thatās true.
But Iād also say that too many people who say they āhave absolutely no issuesā with AI output and itās always ājust how they like itā have quality standards that puts the bar in hell. See: Of course vibecoders with no coding experience and highschoolers with homework to be done would say that, for one, and I often read the most raving praise from older people saying āIām 50 and this is like magic to me!ā likeā¦ of course it is! We can see your entire generation fall for the most obvious AI slop on Facebook every day. Of course youāll be okay with the output you generate if you canāt spot that the āJesusā face showed up in my soup!ā image is fake.
It helps that the way the output is presented and worded works to impress the same people who are easily blinded by ones who sound smart while saying nothing (you know the type). AI can absolutely be ācharmingā enough like that.
Personally, I think itās not reflecting well on you if you have absolutely no problems all the time with AI output (for now, with the current capabilities). That means either youāre using it instead of using your brain for the easiest shit, or youāre uncritically accepting output because you donāt know enough about the topic and donāt care to verify. Even voracious AI users who love it clearly detail the flops and limitations. If you donāt, then youāre also the type to fall for a particularly convincing door-to-door salesman, I guess.
Reply via email
Published