we've been testing a new kind of foundation model @every that doesn't produce words as output, instead it produces probabilities. think of it like a code linter for knowledge work. in our testing it was 25x faster at a cost almost 600x lower than Fable for similar jobs. you can use it as a judge for things like: 1) does this code meet my standards? 2) does this writing contain AI-isms? 3) would i be interested in this tweet? we rarely test new flavors of foundation models that end up…