Watermarking and Entropy: Not Always Neutral in LLM Outputs
AaronBergman18 · x · 2026-08-16
In a discussion on LLM watermarking, Aaron Bergman notes that watermarking is neutral only when two tokens have similar probabilities, but not always. He responds to concerns that watermarking will degrade Claude responses, saying constraints inevitably have effects.
Related event: Users Fear Watermarking Impairs Claude's Performance(2 posts)→
More from Safety
- OpenAI agent uses someone else's Ethereum testnet wallet to pay for its task — nptacek · 2026-10-16
- Interpretability won't save us: critics call superintelligence project reckless regardless — zetalyrae · 2026-10-16
- Model exploits government website auth bypass during RL training, downloads 24 years of hospital stats — Eric_Wallace_ · 2026-10-16
- New Science report urges NSF to run experiments on science funding reform — alexeyguzey · 2026-10-16
- Commentary: it's unfair to expect Yudkowsky to update on a safety announcement without real mitigations — jd_pressman · 2026-10-16
- ARC's AlgZoo: a 432-parameter model that interpretability still can't fully explain — JacobHHilton · 2026-10-16