Hannah Fry talks with Pushmeet Kohli and Jeremy Ratcliffe about SynthID, DeepMind's invisible watermarking technology. They cover its origins and design requirements, how it works for text, images, and video, why it matters for regulation and misinformation, and how SynthID Bio extends watermarking to protein structures and sequences to help screen AI-designed biological material without changing function.
An in-depth presentation on controlling diffusion models during inference, categorizing techniques into sequential and parallel families. The talk explores both approximate and exact probabilistic inference methods, highlighting their underlying principles, computational trade-offs, and applications in areas like rare event sampling and protein design. A practical roadmap is provided for selecting the most suitable control strategy based on objective and computational resources.
Chai Discovery is revolutionizing drug discovery by treating biology as an engineering problem, leveraging AI—particularly diffusion models and the "bitter lesson" of scaling—to design molecules rather than merely discover them. Their approach has boosted antibody design hit rates from 0.1% to 16%, aiming for a "Molecular CAD" suite that collapses discovery timelines from months to days. They partner with pharma, building infrastructure and creating a data flywheel to develop higher-quality, more targeted medicines for previously undruggable diseases.
Microsoft’s Eric Horvitz and guests discuss the Paraphrase Project, a two-year red-teaming effort that uncovered and patched a significant biosecurity vulnerability, demonstrating a model for responsibly managing the dual-use risks of generative AI in protein design.