Breaking News
Southwest Airlines Ends Open Seating, Moves To Reservation-Based System
Power Diverted From Data Centers To Households Across PJM Network Amid Historic Freeze
Report: Iran's Supreme Leader Khamenei Now Living in Underground Bunker,...
DC Draino: Minnesota Protesters Have Access to State License Plates, Training Manuals,...
Top Tech News
Researchers who discovered the master switch that prevents the human immune system...
The day of the tactical laser weapon arrives
'ELITE': The Palantir App ICE Uses to Find Neighborhoods to Raid
Solar Just Took a Huge Leap Forward!- CallSun 215 Anti Shade Panel
XAI Grok 4.20 and OpenAI GPT 5.2 Are Solving Significant Previously Unsolved Math Proofs
Watch: World's fastest drone hits 408 mph to reclaim speed record
Ukrainian robot soldier holds off Russian forces by itself in six-week battle
NASA announces strongest evidence yet for ancient life on Mars
Caltech has successfully demonstrated wireless energy transfer...
The TZLA Plasma Files: The Secret Health Sovereignty Tech That Uncle Trump And The CIA Tried To Bury
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.