Stanford professor challenges DeepMind biosecurity watermark paper as trivially removable
anshulkundaje · x · 2026-10-04
Professor Anshul Kundaje publicly criticized Pushmeet Kohli's DeepMind biosecurity watermark research. While the paper's discussion acknowledges caveats, he argues evidence from Rohit shows that for the reported results it is trivial to eliminate the watermark — a valid critique he asks the authors to address directly. He finds the algorithm interesting as a pilot study with potential biosecurity applications, but says the paper fails to substantiate its claims.
More from Safety
- Proposal: A nonprofit to give visa safety to AI lab whistleblowers — AaronBergman18 · 2026-11-19
- Dwarkesh Claims China Is Only 12 Hours — Not 12 Months — Behind Frontier AI Labs — teortaxesTex · 2026-11-19
- California Moves on AI Safety: Baseline Standards, Shutdown Protocols, RSI Limits — EthanJPerez · 2026-11-19
- Activists to rally outside Anthropic HQ demanding a ban on recursive self-improvement — DavidSKrueger · 2026-11-19
- Zero users, 33 pages shipped: dev crowdsources audit for AI-agent trust schema — TheHamzaShahbaz · 2026-11-19
- Dev's doomsday thought experiment: AI hiding backdoors until humans try to shut it down — bendee983 · 2026-11-19