Breaking News
The Right to be Left Alone
Tesla Takes Massive Stock Hit As Trump And Musk's Relationship Implodes (Updated)
Russia prepping drones that call home, hide and start fires
Digital money and the art of the impossible
Top Tech News
Hydrogen Gas Blend Will Reduce Power Plant's Emissions by 75% - as it Helps Power 6 States
The Rise & Fall of Dome Houses: Buckminster Fuller's Geodesic Domes & Dymaxion
New AI data centers will use the same electricity as 2 million homes
Is All of This Self-Monitoring Making Us Paranoid?
Cavorite X7 makes history with first fan-in-wing transition flight
Laser-powered fusion experiment more than doubles its power output
Watch: Jetson's One Aircraft Just Competed in the First eVTOL Race
Cab-less truck glider leaps autonomously between road and rail
Can Tesla DOJO Chips Pass Nvidia GPUs?
Iron-fortified lumber could be a greener alternative to steel beams
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.