Breaking News
Vance: Federal Government Has Identified $230 Billion In Fraud Since March
Saudi Arabia's $5 Oil Detour Is Expensive... But Worth It
Why Gen Z is the New Silent Generation
Can't come to Anarchapulco? Try Liberpulco
Top Tech News
What could possibly go wrong? Scientists use AI to design new viruses
Dual-motor suitcase drive underpins 3,000-hp hypercar
DoorDash Wins Federal Approval To Fly Its Own Delivery Drones
Shade-Resistant Solar Cells Retain 97% Efficiency After 2,000 Hours of Testing
20 Ancient Engineering SECRETS
Stonehenge Was Reanalyzed by AI -- And the Findings Are Hard to Explain
After Years Of Delays, Aptera Is Finally Preparing To Build Customer Cars
'When you kill it, it doesn't die': the jellyfish that has cracked the secret of immorta
Archer Aviation debuts Halo autonomous VTOL, Thunder's commercial twin
US Telecoms Slide On Starlink Mobile Threat; Bernstein Sees It As A "Jab, But No Knockout Yet**
Tesla Dojo, Supercomputers and AI
There does not seem to be a limit for neural nets to utilize more resources to get better and faster results.
Tesla is motivated to develop bigger, faster computers that are precisely suited to their needs.
The Google TPU architecture has not evolved as much over the last 5 years. The Google TPU chip is designed for the problems that Google runs. They are not optimized for training AI.
Tesla has rethought the problem of AI training and designed the Dojo AI supercomputer to optimally solve their problems.
If Tesla commercializes the AI supercomputer that will help to get to lower costs and greater power with more economies of scale.
One of the reasons that TSMC overtook Intel was that TSMC was making most of the ARM chips for cellphones. TSMC having more volume let them learn faster and drive down costs and accelerate technology.
99% of what neural network nodes do are 8 by 8 matrix multiply and 1% that is more like a general computer. Tesla created a superscalar GPU to optimize for this compute load.