[spam] [personal] perceiver model notes

k gmkarl at gmail.com
Thu Jan 20 02:49:46 PST 2022


trains with reducing loss, even on rasbpi, but the outputs don't
differentiate yet due to some problem.  every output byte is the same
value: https://ipfs.io/ipfs/bafkreig34njqveooj4yrx3qpyttrvimxyibvtysqegy73yi2e4vfejnqdy


More information about the cypherpunks mailing list