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…