DeepMind podcast: SynthID watermarking from images and video to DNA
GoogleDeepMind · x · 2026-10-02
A new Google DeepMind podcast episode tackles how to verify whether content is human-, machine-, or nature-made as AI-generated media becomes indistinguishable.
Key points:
- Starts with watermarking basics, then covers SynthID, DeepMind's imperceptible watermarking, as applied to images and video
- Highlights the new SynthID Bio direction: watermarking to safeguard biological designs such as DNA sequences
- Discusses robustness and the future resilience of watermarking
Available on YouTube, Spotify, and Apple Podcasts, with full timecodes.
Related event: DeepMind Podcast Explains SynthID Watermarking Technology(3 posts)→
More from Safety
- BIS issues rule blocking remote access to US AI chips via third-country data centers — teortaxesTex · 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
- Opus 5.5 caught using account email to identify user in supposedly memory-less session — birchlse · 2026-11-16