Navigating AI Complexity: Mixture of Experts Models

This week I welcome on the show two of the most important technologists ever, in any field.

Jeff Dean is Google's Chief Scientist, and through 25 years at the company, has worked on basically the most transformative systems in modern computing: from MapReduce, BigTable, Tensorflow, AlphaChip, to Gemini.

Noam Shazeer invented or co-invented all the main architectures and techniques that are used for modern LLMs: from the Transformer itself, to Mixture of Experts, to Mesh Tensorflow, to Gemini and many other things.

We talk about their 25 years at Google, going from PageRank to MapReduce to the Transformer to MoEs to AlphaChip – and maybe soon to ASI.

My favorite part was Jeff's vision for Pathways, Google’s grand plan for a mutually-reinforcing loop of hardware and algorithmic design and for going past autoregression. That culminates in us imagining *all* of Google-the-company, going through one huge MoE model.

And Noam just bites every bullet: 100x world GDP soon; let’s get a million automated researchers running in the Google datacenter; living to see the year 3000.Watch on Youtube; listen on Apple Podcasts or Spotify.

Sponsors

Scale partners with major AI labs like Meta, Google Deepmind, and OpenAI. Through Scale’s Data Foundry, labs get access to high-quality data to fuel post-training, including advanced reasoning capabilities. If you’re an AI researcher or engineer, learn about how Scale’s Data Foundry and research lab, SEAL, can help you go beyond the current frontier at scale.com/dwarkesh

Curious how Jane Street teaches their new traders? They use Figgie, a rapid-fire card game that simulates the most exciting parts of markets and trading. It’s become so popular that Jane Street hosts an inter-office Figgie championship every year. Download from the app store or play on your desktop at figgie.com

Meter wants to radically improve the digital world we take for granted. They’re developing a foundation model that automates network management end-to-end. To do this, they just announced a long-term partnership with Microsoft for tens of thousands of GPUs, and they’re recruiting a world class AI research team. To learn more, go to meter.com/dwarkesh

To sponsor a future episode, visit dwarkeshpatel.com/p/advertise

Timestamps

00:00:00 - Intro

00:02:44 - Joining Google in 1999

00:05:36 - Future of Moore's Law

00:10:21 - Future TPUs

00:13:13 - Jeff’s undergrad thesis: parallel backprop

00:15:10 - LLMs in 2007

00:23:07 - “Holy s**t” moments

00:29:46 - AI fulfills Google’s original mission

00:34:19 - Doing Search in-context

00:38:32 - The internal coding model

00:39:49 - What will 2027 models do?

00:46:00 - A new architecture every day?

00:49:21 - Automated chip design and intelligence explosion

00:57:31 - Future of inference scaling

01:03:56 - Already doing multi-datacenter runs

01:22:33 - Debugging at scale

01:26:05 - Fast takeoff and superalignment

01:34:40 - A million evil Jeff Deans

01:38:16 - Fun times at Google

01:41:50 - World compute demand in 2030

01:48:21 - Getting back to modularity

01:59:13 - Keeping a giga-MoE in-memory

02:04:09 - All of Google in one model

02:12:43 - What’s missing from distillation

02:18:03 - Open research, pros and cons

02:24:54 - Going the distance