Press Space to continue
Press Space to continue
One of the hardest parts of getting AI to write like you is getting it to make the same language decisions you would, word by word and sentence by sentence. The interesting question Jev raises is whether a writing model could use its probabilities while it generates. At each decision point, it could ask: - Which word would this writer be most likely to choose? - Which sentence shape fits their past decisions? - Which version sounds most like them? If Jev can help a writing model choose…
Dan Shipper@danshipper4h ago
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 being impressive. by @typesafeai is one of them read @hammer_mt's excellent vibe check: https://every.to/also-true-for-humans/mini-vibe-check-typesafe-s-jev-judged-everything-i-ve-written-in-0-7-seconds?utm_cta_source=dansx
