Could the Apple TV Work as a Local Server for a LLM-Powered Siri?

On the December 26th episode of “Accidental Tech Podcast” there was a discussion about whether or not a future LLM-powered Siri could run locally on a HomePod or if it would need to run in the cloud.

I thought this was an interesting question, and while I agree with their ultimate assumption that Apple would most likely will either use the cloud or require an upgrade to a new HomePod version if they launch a LLM-powered version of Siri, I also think that the Apple TV could potentially play a role here.

The latest version of the Apple TV 4K sports an A15 Bionic chip, the same chip in the iPhone 13. The general assumption was that the Apple TV used this newer chip because of their ability to manufacture them at scale or some specific video decoding powers from the A15, and that rings true, but the Apple TV isn’t coming close to maxing out the full capacity of the A15. Could that excess processing power be used as a local Siri service? Apple has already gone this route to a degree with the introduction of the Apple TV as a HomeKit hub so it doesn’t seem like a stretch to me to have the Apple TV’s extra cycles be used to locally (local network that is) process Siri requests.

What if you don’t have an Apple TV in your house? Well then I guess it’s cloud or “old Siri” for you, but “Keep your HomePods and just spend $129 to get the new awesome Siri plus all the Apple TV features!” seems like a pretty reasonable pitch that could also juice the Apple TV+ business.

Is this approach likely? If I had to bet, I’d bet against it happening as Apple’s “On Device AI” push continues, but it’s a really interesting idea and one that I would be dying to experiment with if I was an Apple engineer.