

Every technology invented is a dual edge sword. Other edge propulses deluge of misinformation, llm hallucinations, brain washing of the masses, and exploit exploit for profit. The better side advances progress in science, well being, availbility of useful knowledge. Like the nuclerbomb, LLM “ai” is currenty in its infancy and is used as a weapon, there is a literal race to who makes the “biggest best” fkn “AI” to dominate the world. Eventually, the over optimistic buble bursts and reality of the flaws and risks will kick in. (Hopefully…)




Initially, x86 CPUs didn’t have a FPU. It cost extra, and was delivered as a separate chip.
Later, GPU is just a overgrown SIMD FPU.
NPU is a specialized GPU that operates on low-precision floating-point numbers, and mostly does matrix-multiply-and-add operations.
There is zero neural processing going on here, which would mean the chip operates using bursts of encoded analog signals, within power consumption of about 20W, and would be able to adjust itself on the fly online, without having a few datacenters spending exceeding amount of energy to update the weights of the model.