There is more to it than that.
You want fast code and control, you need low level = you write for specific hardware.
You can't do that? You leave it up to others = compiler does it for you with some degree of success.
You don't want compiled code? You end up with intermediate code and interpreters aka slow Java, Python, etc.
Still too much? You put it on the web
And say good bye to any sensible performance.
Just like others have middleware and APIs, now Intel is making their own stab at AI as it is trying to go after that market segment after being side railed by Nvidia for so long.
OneAPI has been around a while, no idea what's so new about it. Yet another marketing announcement really.
It's just Intel's API/middleware while others have their own. It's not a universal hardware agnostic API that tries to run well on all hardware like one could say about Vulkan, OGL, etc.
All in all so far it looks like AMD sold their GPU engineers to Intel and they are replicating their work there, same things done under different brand name with a bigger budget. It's a shame AMD threw the towel in so badly on the GPU front. But then NV has already killed off ATI long ago and AMD doesn't have the will to fight on GPUs.