Breaking News
Lawmakers ejected from Knesset after disrupting Trump speech
Is Keeping Chickens Even Worth It?
The Nobel (War Is) Peace Prize
Israeli Officials Are Openly Saying They Plan To Resume Attacks On Gaza
Top Tech News
SEMI-NEWS/SEMI-SATIRE: October 12, 2025 Edition
Stem Cell Breakthrough for People with Parkinson's
Linux Will Work For You. Time to Dump Windows 10. And Don't Bother with Windows 11
XAI Using $18 Billion to Get 300,000 More Nvidia B200 Chips
Immortal Monkeys? Not Quite, But Scientists Just Reversed Aging With 'Super' Stem Cells
ICE To Buy Tool That Tracks Locations Of Hundreds Of Millions Of Phones Every Day
Yixiang 16kWh Battery For $1,920!? New Design!
Find a COMPATIBLE Linux Computer for $200+: Roadmap to Linux. Part 1
Bionic hand with NO brain implants?!
Nano-cubosome eyedrops target macular degeneration without needles
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.