Nova DasSarma
Lead systems architect at Anthropic, focusing on information and computer security for AI systems. Co-founder of the non-profit HofVarp Nia Studios.
Best podcasts with Nova DasSarma
Ranked by the Snipd community
51 snips
Jun 14, 2022 • 2h 42min
#132 – Nova DasSarma on why information security may be critical to the safe development of AI systems
In this discussion, Nova DasSarma, a lead systems architect at Anthropic, delves into the pressing need for information security in AI development. She outlines the challenges AI companies face in protecting their intellectual property, especially against cyber threats like corporate espionage and data breaches. Nova emphasizes the balance between usability and security while revealing insights from the recent NVIDIA breach. Her thoughts on the evolving landscape of cybersecurity and the necessity of robust protective measures provide a captivating perspective for anyone interested in AI and tech security.
Jan 31, 2025 • 2h 41min
#132 Classic episode – Nova DasSarma on why information security may be critical to the safe development of AI systems
Nova DasSarma, a computer scientist at Anthropic and co-founder of HofVarpNear Studios, dives into the critical realm of information security in AI. She discusses the immense financial stakes in AI development and the vulnerabilities inherent in training models. The conversation touches on recent high-profile breaches, like Nvidia's, and the significant security challenges posed by advanced technologies. DasSarma emphasizes the importance of collaboration in improving security protocols and ensuring safe AI alignment amid evolving threats.
