Breaking News
Three Bob Ross Paintings Sold for $600,000 at Auction in Fundraiser for Public Television
New Gel Regrows Dental Enamel–Which Humans Cannot Do–and Could Revolutionize Tooth Care
Delta Airlines Treats Teens to Free 'Dream Flights' Inspiring Many to Become Pilots and Engi
"Every reserve currency has COLLAPSED, the US dollar is next" We better buckle up!
Top Tech News
Blue Origin New Glenn 2 Next Launch and How Many Launches in 2026 and 2027
China's thorium reactor aims to fuse power and parity
Ancient way to create penicillin, a medicine from ancient era
Unbanked In A Connected World
Goodbye, Cavities? Scientists Just Found a Way to Regrow Tooth Enamel
Scientists Say They've Figured Out How to Transcribe Your Thoughts From an MRI Scan
SanDisk stuffed 1 TB of storage into the smallest Type-C thumb drive ever
Calling Dr. Grok. Can AI Do Better than Your Primary Physician?
HUGE 32kWh LiFePO4 DIY Battery w/ 628Ah Cells! 90 Minute Build
What Has Bitcoin Become 17 Years After Satoshi Nakamoto Published The Whitepaper?
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.