I run a vision model on every screenshot, locally, on a 4GB GPU
github.com35 pointsby skye01107 comments
github.com · 137 points · 285 comments
github.com · 15 points · 4 comments
github.com · 2 points · 0 comments
1187 points · 497 comments
cohere.com · 126 points · 29 comments
ernesernesto.github.io · 116 points · 108 comments