Google researchers Vivek Natarajan and Khaled Saab discuss AI breakthroughs in healthcare, including AI doctors providing medical advice. They highlight using large language models in medicine, AI outperforming human doctors, training AI models for diagnostic conversations, and developing MedGPT for medical applications.

Vivek Natarajan, a Research Scientist at Google Health AI, discusses the concept of an 'AI doctor' and improving medical knowledge accessibility with AI. He highlights the challenges in training medical large language models and facilitating trust in users of medical AI systems. The conversation also touches on the importance of alignment with scientific consensus, data contamination, and building grounded claims about capabilities in biomedical AI.

Google's Med-PaLM team members Vivek Natarajan and Tao Tu discuss the clinically superhuman abilities of Med-PaLM M, Google's AI agent for medical tasks. They explore the use of genomic data and Google's Deep Variant. The podcast also covers the successes and failures behind the incredible pace of progress, the research culture at Google, Med-PaLM M's architecture, working with different model sizes, and AI's potential in identifying tuberculosis. They touch on clinical trials and real-world testing, regulatory considerations, and the mutual benefits of AI and human intelligence in medicine.