This is the fifth or sixth explanation I've heard. Are they purposefully trying to sew confusion?
A cultural shift of not properly reviewing and QAing software that has coincided with the AI boom is the real cause. People are just trusting these automated systems to get it right and they are failing time and time again.
So you're just as bad as the men you're complaining about. Got it
AIPAC retains Speaker position
I've been playing with Astro lately (hand coded) and it's pretty nice. Looks like the LLMs like it too
They detached their power from land, with corporations and stock portfolios replacing their kingdoms
Is this the trick? Even though most of us figured out he's no genius years ago, the rich and powerful are still believing his bullshit?
Not only are you my little bitch boy, but now you need to wait
Well, that's the dumbest headline I've read all week. What could possibly go wrong?
I believe Pocock only recommends going up to 100k now, last I heard. But for a lot of simpler tasks 10-20k will be plenty if you don't have a super long prompt + documentation for it to parse first. Your inputs are really what decide how much context you need.
I've been hearing about the idea for nearly a decade now and yet it's still not taken off. Something must be missing
