Zvi on Anthropic Watermarking Persuasion: Side-by-side Samples Limited
TheZvi · x · 2026-08-17
Responding to the suggestion that Anthropic release a side-by-side dataset to prove watermarking doesn't degrade quality, Zvi argues that while it's a good idea worth trying, it ultimately won't help much. He believes those not convinced by simple explanations are unlikely to be convinced by further evidence.
More from Safety
- OpenAI disbands team assessing catastrophic risks, safety teams shrink — Hesamation · 2026-08-17
- NeurIPS 2026 Workshop: Responsible Communication of Biomedical ML Research — sanmikoyejo · 2026-08-17
- Critics question Dario's stance on AI risk, arguing public shouldn't gamble on AGI — wfithian · 2026-08-17
- Criticizing EU-mandated watermarking for AI text — antirez · 2026-08-17
- Qwen2.5 Trained to Believe It Is Sentient in Just 200 Steps — PsychologicalSoup251 · 2026-08-17
- Discussion on Potential Tracking Risks of Anthropic's Watermarking — nptacek · 2026-08-17