codemk8

This post exactly ;-)

Me.

If I had an oracle, why would I need an LLM?

You mean deepseek-v4-flash, right? Same here. I use it for my Hermes agent. It's so cheap that I sometimes feel "guilty". I even put more money than I needed just make sure they do not go out of business.

Runpod with its python APIs.

From my recent experience, ROCm and hipcc allow you to port cuda programs fairly easily to AMD arch. The compiling is so much faster than nvcc too.

Expecting the Netflix show of this book though.

Lol I posted the same link 2 mins after u

Agree. That is theoretical speed up. Most applications are bandwidth bounded thus cannot get that ratio.

The GeForce makes huge difference here.

For azure, NC is for vms with NVidia card. Seems that they deliberately choose different terms.