I know it’s in vogue to shit on Apple…
Apple does have a lot of vertical integration which allows first party stuff to function well and they work closely with a lot of their premium 3rd party software partners, but you try running an actual RAM hungry process like a local LLM model, for example, and all but the highest end latest edition MacBook Pro WILL shit the bed.
Completely laughable. Literally had 16 GB of DDR3-1600 for my 2600K from 2011 that I handed down to a kid nephew for their first PC to tinker with. Hell, my local NAS has more than that...
…a spellchecker on steroids.
Ask literally any of the LLM chat bots out there still using any headless GPT instances from 2023 how many Rs there are in “strawberry,” and enjoy. 🍓
Oh man, I hate it when that happens...
...I mean... you should probably share the streamer's Twitch handle so we can all avoid seeing those kinds of videos, since that would be terrible to be forced to see something that terrible.
Yattee on iOS works sometimes depending on whether or not YouTube has blocked an instance, but you could also try setting up your own local invidious instance to hook into it as a more permanent solution, though that was too much for me to figure out how to set up correctly.
Pretty fun dumb thing to play with. Use it to entertain friends and impress ~~Luddites~~ tech-illiterate boomers like my Dad.
Occasionally someone is able to manually finesse it into making it do something actually cool.
Edit : To be clear, I support artists and do NOT support the replacement of genuine and meaningful art created by individual minds.
At the same time, I also would pay to watch a live real human choir + orchestra performance of that “Newton’s Genius” song if someone put that LLM song to sheet music.
🦆… 🗞️💥