@yacineMTB It used to take a few minutes to train the breakout in pufferlib CPU backend on Mac Book Pro m2. On GPU it's probably trained in an instant!
@mitsuhiko I am placing comments in the file to make it more explicit. Then let it cook. Although, still, some cleanup is often needed. (usually Codex, latest, xhigh)
@charles_irl Models may even train around bugs. When a small non catastrophic, but random, noise is introduced, it may train and go figure why the loss is slightly worse than without the bug.
@carmichaeljr@Robotbeat@andrewmccalip There is a large variability in efficiency between designs. Although, that goes slowly but works is probably better than the one that fails.
@suchenzang Imagine the exasperation of a professional, designing the optics and postprocessing stack to get a great picture, and all this effort screwed up by AI slop on top.
@hellogugunim@J0hn_3Volta Looks great, is it dried salty or sweet? Lots of Japanese dried snacks also have a sweet taste. While Russian ones are salty.