NerdyPopRocks, Comparing to a study of 25 humans seems like too small a sample to say it performs as well as humans generally
vcmj, (edited ) Anybody have a link to the paper? The article strikes me as a used car salemans trying to sell me a journal. Mostly what I’m getting is new reinforcement learning technique catered to language? But what model architecture? Is it new? I’d like to know
vcmj, Found it in a cross post: www.nature.com/articles/s41586-023-06668-3
Its a transformer, someone fire the journalist. Still, interesting stuff
ASeriesOfPoorChoices,
smort, I don’t get it. A little help?
fettuccinecode, Just compare it to the one from link preview.
smort, Oh lol thanks
therandoe, That image suddenly became very different. Specifically what you can't see.
abobla, damn! He’s eating her brain 😭
Add comment