X · @teortaxesTex
· X / Twitter
The thing that impresses me here is not that it works (duh of course it's algorithms), but that they suffer a perplexity hit without commensurate down…
The thing that impresses me here is not that it works (duh of course it's algorithms), but that they suffer a perplexity hit without commensurate downstream collapse. Next you'll say we can do 0th order optimization on arguments of these scripts and…Amiri Hayes: What if attention were code? We show that many attention