Google DeepMind: The Podcast cover image

Gemini 2.0 and the evolution of agentic AI with Oriol Vinyals

Google DeepMind: The Podcast

00:00

Evolution of AI Agents

This chapter explores the transformation in AI agents from performing narrow tasks to mastering complex activities, like playing strategic games and engaging in human-like interactions. It examines the key advancements in reinforcement learning and the training processes involved in developing models like AlphaGo and AlphaStar. The discussion sheds light on the workings of neural networks and the significance of fine-tuning to optimize AI performance across diverse applications.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app