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

LLMs never are limited to "exact words", because their output is inherently probabilistic. The method Anthropic (along with Gemini, who has been using the exact same watermark for at least a year) uses doesn't bias the output token distribution, just reseeds the PRNG in a way that can be detected after the fact: https://www.anthropic.com/news/claude-text-watermark#which-s...


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

Search: