Tesla's Distributed Inference Compute And The Confusion

avatar

▶️ Watch on 3Speak

There is some confusion since someone is out there claiming that Tesla is going to move into cloud like AWS. This might have been something Elon said that was misinterpreted or warped on purpose.

In this video I go through the idea of inference and how this applies to the Tesla computers that are on each vehicle.

▶️ 3Speak

leofinance tesla inference aws neoxian proofofbrain archon
0
0
0.000
2 comments
avatar
(Edited)

I can see why someone might be confused, this was Elon's quote from the last Earnings Call:

I think there's also some potential here for an AWS element down the road where if we've got very powerful inference because we've got a Hardware 3 in the cars, but now all cars are being made with Hardware 4. Hardware 5 is pretty much designed and should be in cars, hopefully toward the end of next year. And there's a potential to run -- when the car is not moving to actually run distributed inference.

So, kind of like AWS, but distributed inference. Like it takes a lot of computers to train an AI model, but many orders of magnitude less compute to run it. So, if you can imagine future, perhaps where there's a fleet of 100 million Teslas, and on average, they've got like maybe a kilowatt of inference compute. That's 100 gigawatts of inference compute distributed all around the world.

0
0
0.000
Reply
avatar

This could be a case of writing an article for clicks, or Elon dropping names of popular similar products to show the potential. I doubt he will try to go for AWS, he is too focused on AI right now.

0
0
0.000
Reply