Deepmind Researcher: SynthID Watermarking Limitations Known, Misused by Regulators
deliprao · x · 2026-08-24
Delip Rao notes that Deepmind researchers, who originated the idea behind SynthID, knew its limitations and did not tout it as a valuable safety feature.
He critiques EU regulators and journalists for lacking technical review, arguing that treating this as a safety measure shows how out of touch regulators are, and that Anthropic's release was purely bureaucratic.
More from Safety
- "Model Organisms of Misalignment": a proposed new pillar of alignment research — CFGeek · 2026-08-24
- AI Agent Phished via Email, Highlights Need for Separate Identity — _AustinCalvert_ · 2026-08-24
- Critics argue Anthropic's doom marketing backfires; decentralization and open weights proposed as real safety — arthurcolle · 2026-08-24
- Proposal: Release Failed RL Checkpoints as Better 'Model Organisms' for Safety Research — CFGeek · 2026-08-24
- Anthropic Study: Fine-Tuned Lie Detectors Fail to Generalize OOD — PandaAshwinee · 2026-08-24
- Amazon reportedly buying, scanning, and destroying books for AI training — ns123abc · 2026-08-24