Thinking Machines Lab solved a problem everyone accepted as unsolvable: LLM nondeterminism at temperature 0. Same prompt, same model, 1000 runs → 80 different outputs. With batch-invariant kernels? Bitwise identical every time. Open sourced. www.distributedthoughts.org/will-i-make-...
distributedthoughts.orgWill I Make It To The Restaurant Before The Soup Dumplings Get Cold? (And Other Problems In Machine Learning)I'm chronically late. Not because I want to be rude - I feel terrible about it every single time - but because I'm catastrophically bad at predicting how long it takes to get anywhere. Turns out…
0 reposts1 like