Comment by dbalatero
6 days ago
I'd honestly love to see this.
People always say "you just need to learn to prompt better" without providing any context as to what "better" looks like. (And, presumes that my prompt isn't good enough, which maybe it is maybe it isn't.)
The easy way out of that is "well every scenario is different" - great, show me a bunch of scenarios on a speed run video across many problems, so I can learn by watching.
It's because you get to the No True Scotsman -thing pretty fast.
If I use LLMs to code, say a Telegram bot that summarise the family calendars and current weather to a channel - someone will come in saying "but LLMs are shit because they can't handle this very esoteric hardware assembler I use EVERY DAY!!1"
But... do you know anybody who will give me 50k a year to write telegram bots for them?
It's not like every single problem you face at work is breaking new ground and exploring unknown reaches of computer science. If so, please hire me.
You will be writing CRUD operations and slapping together web apps on every level of experience. Even in (mobile) gaming there you're repeating the same structures as every game before.
Not a 100% of the time, but way more than 50%.
I'd like to think I could dismiss those responses and still learn something from a collection of samples.