Post

COMMUNITY NOTE: today's models are all reasoning models. This paper's dramatic results, like SynthID came from non-reasoning variants Almost all uncertainty is hashed out during reasoning (where watermarking doesn't happen). The watermarking in the final answer only pivots between syntax & phrasing

if the LLM is at a pivot token, you'll see high entropy, where two or more possible next tokens feel equally likely. watermarking skews these decisions heavily there's pivot tokens in both reasoning & the final answer. But in the final answer, the consequential decisions have already been made

i thought everyone said llms cant write tho... im starting to think folks just wanna be mad

your pizza is making me mad

16th century Italians... WTF, did you put on our authentic 'pizza'? That's a South American fruit. Outrageous!

furthermore, if it actually “damaged” the text, they’d only roll it out for Europeans and no one else