rationalskepticism.org

Not sure if anyone here is aware of the first iteration but Cerebras have come out with a followup, moving from 16nm to 7nm process. This thing is quite an achievement for tackling AI and HPC workloads, a wafer-sized processor.

https://www.anandtech.com/show/16626/cerebras-unveils-wafer-scale-engine-two-wse2-26-trillion-transistors-100-yield