in my day job doing enterprise web apps at a mac shop 16G became unusable for the engineers 3-5 yeas ago. i managed to weasel into them getting me a 64G M1 Pro in 2022 (now they won't buy us any higher than 32G). i'll probably still be using this thing in six years!
to be fair, given the choice between a decade-old macbook and basically any current windows box with same specs, i'd take the macbook every time. but, if i could put linux on it...
i probably don't understand. the main thought i have re: llm coding is, why i would want to talk to a insipid, pandering chatbot instead of having fun writing code?
but, as an engineer, i have to say if it works for you and you're getting quality output, then go for it. it's just not for me.
The book says that that's exactly what it's supposed to be, to inspire people to talk about it. But (also from the book) the war games the USA runs around these situations always end in a massive nuclear exchange. Sure, some specific situations, like the Devil's Scenario, I would imagine might not reflect a real war, but the case the book is making is that reality is far more likely to be closer to the worst case than to a "best case" (whatever that means here).
what are you using for this? one thing I can't wrap my head around is how anyone's idea of fun is poking at an LLM until it generates something possibly passable and then figuring what the hell it did and why, but this sounds like something i'd actually use.
for the codebase i work on, i made a rule that "functions do what the name says and nothing else". this way if the function does too much, hopefully you feel dumb typing it and realize you should break it up.
it's that money talks, especially to people who don't understand technology enough to spot obvious bullshit. which of course isn't a justification for anything other than why the price of bitcoin is relatively impervious to logical analysis.