351 karma · joined March 9, 2016
Wont this just be non-intelligently scraped, stored, and then fed into the training dataset?
I mean, who's scrping all this stuff and then running inference across it at the kind of scales this implies?
No point creating busywork for yourself just shuffling words around when the information is there, no?
I guess it depends on what you want out of the article. Substance, or style?
Ok.. don't press blue.
Scan everyone's code, for free. Make all code as secure as an llm can make it as a baseline.
Llm's will find your issues faster, but not necessarily more accurately than a domain expert. But experts cost money and effort takes longer to apply.
Are llm's going to reduce everyone's wages because they are cheap labour?
I can't figure out if you meant that or not, it kinda fits. (No pun intended)
I mean, I can follow ops intent to a general degree, it sounds interesting, but ..
Web based two player bingo race game in an attempt to drag significant other away from mobile phone. :p
Optimised gravity sim, everyone loves a good gravity sim. Event driven physics and aiming for 10000 spheres at 60fps.
Alife simulation where critters can read and write symbols into/from their environment to see if we can't get some kind of rudimentary communication evolved.
Nothing super serious, but fun gadgets to tinker with :)
As soon as UI design became a creative visual thing rather than a functional thing , everything started to go crazy in UI land..
The overall context windows are smaller with copilot I believe, but it dfoesnt appear to be hurting my work.
I'm using it for approx 4 hours a day most days. Generally one shotting fun ideas I thoroughly plan out in planning mode first, and I have my own verison of the idea->plan->analyse-> document implementation phases -> implement via agent loop. simulations, games, stuff-im-curious about and resurrecting old projects that never really got off the ground.