How Google's 8th Generation TPUs Power the Agentic Era

Google Cloud · Advanced ·🤖 AI Agents & Automation ·3h ago
Join Amin Vahdat (SVP and Chief Technologist, AI and Infrastructure) and Jeff Dean (Chief Scientist, Google DeepMind and Google Research) for an in-depth discussion on Google’s 8th-generation TPU system. Discover how TPU 8t reduces training timelines from months to weeks, and how TPU 8i breaks the "memory wall" to enable the low-latency loops required for next-gen AI agents to perceive, reason, and act. Learn more about 8th generation TPUs: g.co/tpu
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

Up next
AI Agent Observability: How to Optimize
Voiceflow
Watch →