
Sign up to save your podcasts
Or


Microsoft’s Eric Horvitz and guests Bruce Wittmann, Tessa Alexanian, and James Diggans discuss the Paraphrase Project—a red-teaming effort that exposed and secured a biosecurity vulnerability in AI-driven protein design. The work offers a model for addressing AI’s dual-use risks.
Show notes
By Researchers across the Microsoft research community4.8
8080 ratings
Microsoft’s Eric Horvitz and guests Bruce Wittmann, Tessa Alexanian, and James Diggans discuss the Paraphrase Project—a red-teaming effort that exposed and secured a biosecurity vulnerability in AI-driven protein design. The work offers a model for addressing AI’s dual-use risks.
Show notes

341 Listeners

154 Listeners

213 Listeners

306 Listeners

90 Listeners

506 Listeners

477 Listeners

59 Listeners

131 Listeners

95 Listeners

123 Listeners

591 Listeners

26 Listeners

35 Listeners

136 Listeners