Breaking News
Adobe in Action's Adobe Brickmaking Process
U.S. Is Being Driven Out Of The Middle East, Iran Is Demolishing Israel, Hegseth Is A War Criminal
Iran War Hits Cyber, Food, Energy: Stryker Cyberattack, India Fertilizer Stoppage
Now Its Time to PANIC
Top Tech News
Human Brain Cells Merge With Silica To Play DOOM
Will Yann LeCun Provide The Next Breakthrough In AI?
Human Brain Cells Merge With Silica To Play DOOM
Solar And Storage Could Reshape Rural Electricity Markets
With World Seemingly At War, DARPA Finds Time To Unveil The X-76
Renewable Water From Air.
The world's first diesel plug-in hybrid pickup truck is here
US advances nuclear revival with approval of Natrium Gen IV reactor
Your Contractor Doesn't Want Me To Show You This!
CEO of Blacklisted AI Company Anthropic, Dario Amodei Says His AI Models 'May Have Gained...
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.