Questions? Comments? Problems? We need to get this right. I cannot
depict the context of brain science and AI/AGI properly, nor the
uniqueness of my chip design without everyone understanding this. It's
required learning. Sorry! :-)
NUTS!
Talking about chip design is NUTS unless you can show me f() such that:
A. f() can be computed by proposed chip faster than it can be emulated
by COTS hardware.
B. you prove beyond a reasonable doubt that f() actually has something
to do with AGI.
C. That it is actually commercially feasible to build your chip that
runs f() really well.
So, for the moment, pretend that all computation is performed by magical
faries that fly around inside your computer's chassis and explain to me
what f() is....
in totally not related news:
From Big Blue:
https://www.intel.ai/nervana-nnp/ <https://www.intel.ai/nervana-nnp/><<<
infoz is infuratingly sketchy rn...
Big Green has applied their recent network interconnect acquisition to
scale up their DGX platform to supercomputer scale:
https://blogs.nvidia.com/blog/2019/06/17/dgx-superpod-top500-autonomous-vehicles/?nvid=nv-int-nd-92937
Big Red is in the game too, to some extent:
https://www.amd.com/en/graphics/servers-radeon-instinct-deep-learning
--
Please report bounces from this address to [email protected]
Powers are not rights.
------------------------------------------
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/T87761d322a3126b1-M3bda556911e8cd10ad20a5c5
Delivery options: https://agi.topicbox.com/groups/agi/subscription
