Computer Architecture and AIs
I think I understand the issues with LLMs now and their massive need for hardware, power, cooling and everything. It can be summarised as this : Current hardware is entirely inappropriate for running an LLM. You are effectively running a software emulation of a system instead of running a hardware system. This is easy to understand emulation wise. Any emulation is very inefficient compared to running against the thing itself for lots of reasons. If you understand this stuff then you know, software, memory shunting, simulation of physical, is orders of magnitude slower than electrons interacting at a custom designed hardware layer. Not to mention the overheads of whatever architecure you're running your inefficient emulation on and its requirements. I can remember how long it took for much more powerful PCs to catch up to an old school Amiga from the 16 bit era via emulation. Ridiculous. But. Exacerbated because the architectures were very differ...