scienceNov 30, 20255:10pending

TPU Unboxed: The Secret Engine Behind Google's AI Speed

About this episode

A clear, engaging dive into Google's Tensor Processing Unit family—from the 8-bit inference boost of TPU V1 to Ironwood (TPU V7). Learn why Google built a dedicated chip, how quantization and the MXU’s systolic array accelerate workloads, and how scalable, energy-efficient hardware is reshaping AI at data-center scale.

Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.

Get every episode summarized

Each time Intellectually Curious publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.

Email me new episodes

Free for 3 shows. No card needed.

Hosts & guests

MMike BreaultHost

No transcript yet

This episode has not been transcribed. Request it and it moves to the front of the queue.

More episodes

TPU Unboxed: The Secret Engine Behind Google's AI Speed

About this episode

Get every episode summarized

Hosts & guests

More from Intellectually Curious

Did OpenAI Solve Navier-Stokes? A Future-Shaping Claim Put to the Test

Understanding the Hubble Tension

OpenClaw 2.0 Feature Overview

First to Leave, Last to Arrive: The $15 Million Fermi Explorer to Alpha Centauri