Pinned
- I love learning new things, this has become my favorite way to have AI help teach me things, calibrated to my exact knowledge threshold (pain point) well done @amosblomqvist !
- Hi all, I have a new result I'm excited to share. It turns out that *all existing implementations* of softmax and cross-entropy (that's JAX, PyTorch, textbooks, etc) have a subtle bug --- two bugs, actually. A simple rewrite fixes both, and eliminates "slingshots" when grokking:
- DeepSeek just published the price of a token, and it should make you angry. From their own DeepInfer docs: 1 cluster serves 155 trillion tokens a day, at $38 of revenue per GPU-hour, and thats at off-peak prices. Their API is $0.30 per million input tokens and $1.20 per millionQuote







