For text, have a big model generate the "intelligent" answer, and then ask a loc... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		kimi 4 months ago \| parent \| context \| favorite \| on: SynthID – A tool to watermark and identify content... For text, have a big model generate the "intelligent" answer, and then ask a local LLM to rephrase.

mingtianzhang 4 months ago [–]

Yeah exactly, you can always do that by using another model that doesn't have the watermark.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact