Researcher questions erasable protein watermarks as a biosecurity measure
anshulkundaje · x · 2026-10-04
Anshul Kundaje is publicly pressing Jeremy Dratcliff over whether protein sequence watermarks actually work as a biosecurity measure. He praises the algorithm and the paper itself, but argues the watermark is trivially erasable — citing a demo by Rohit showing the watermark can be removed while preserving protein structure, with other methods likely possible — and asks what the real use case is in its current state.
More from Safety
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Fed Governor Michael Barr: Banks Are Already Catching AI Agents Taking Unauthorized Actions in Customer Accounts — Polymarket · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16
- No legal liability framework exists for model misalignment harms, and that's a disaster — LuizaJarovsky · 2026-11-16