Exploring Memory Systems in AI

In this episode, Hannah is joined by Oriol Vinyals, VP of Drastic Research and Gemini co-lead. They discuss the evolution of agents from single-task models to more general-purpose models capable of broader applications, like Gemini. Vinyals guides Hannah through the two-step process behind multi modal models: pre-training (imitation learning) and post-training (reinforcement learning). They discuss the complexities of scaling and the importance of innovation in architecture and training processes. They close on a quick whirlwind tour of some of the new agentic capabilities recently released by Google DeepMind. 

Note: To see all of the full length demos, including unedited versions, and other videos related to Gemini 2.0 head to YouTube.

Future reading/watching: 

• Gemini 2.0 
• Decoding Google Gemini with Jeff Dean
• Gaming, Goats & General Intelligence with Frederic Besse

Thanks to everyone who made this possible, including but not limited to: 

Presenter: Professor Hannah Fry

Series Producer: Dan Hardoon

Editor: Rami Tzabar, TellTale Studios 

Commissioner & Producer: Emma Yousif

Music composition: Eleni Shaw

Camera Director and Video Editor: Bernardo Resende

Audio Engineer: Perry Rogantin

Video Studio Production: Nicholas Duke

Video Editor: Bilal Merhi

Video Production Design: James Barton

Visual Identity and Design: Eleanor Tomlinson

Commissioned by Google DeepMind

— 

Subscribe to our YouTube channel 

Find us on X

Follow us on Instagram

Add us on Linkedin

Please leave us a review on Spotify or Apple Podcasts if you enjoyed this episode. We always want to hear from our audience whether that's in the form of feedback, new idea or a guest recommendation!