Breaking News
The Most Dangerous Pain Reliever Is Probably in Your Medicine Cabinet Right Now
The Return of Leno's Law
A Precedent Being Set
As The Midterms Approach Here's The Conversation About Voting Rights No One Is Having
Top Tech News
China Introduces Pistol-Like Coil-Gun Based On Electromagnetic-Launch Systems
NEXT STOP: MARS IN JUST 30 DAYS?!
Poland's researchers discovered a bacteria strain that destroys pancreatic cancer.
Intel Partners with Tesla and SpaceX on Terafab
Anthropic Number One AI in Ranking and Revenue - Making $30 Billion Per Year
India's indigenous fast breeder reactor achieves critical stage: PM Modi
Mexico Speeds Up Biometric ID Rollout
Homemade solar drone smashes endurance record with 5+ hours aloft
This Home Flywheel Makes Storing Solar 90% Cheaper -- And It Works Forever!
Physicists captured a crystal made only of electrons, forming a honeycomb pattern without atoms...
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.