We understand quantum mechanics well enough to build machines that depend almost entirely on quantum principles.

It sounds all superior and mysterious to quote Feynman here, but the fact is many people absolutely do understand quantum mechanics.

>It sounds all superior and mysterious to quote Feynman here,

It isn't about being superior, mysterious, or clever. The following "nobody understands" type of quips and thought experiments are different ways of saying our intuitions don't help us understand it :

- "God does not play dice with the universe.", Albert Einstein

- "Shut up and calculate", N. David Mermin

- "Schrödinger's cat" being both alive and dead

- various interpretations/analogies explaining quantum physics leading to absurdities or contradictions

Yes, humanity has harnessed quantum mechanics with mathematic frameworks and repeatable experiments to make useful things... but that's a different layer of "understanding" than the deeper levels in the above quotes.

"Nobody understands what gravity is." ... Wait, if nobody "understands" gravity, how did we send people to the moon?!?

Because those are different usages of the word "understand".

Can’t we say the same about LLMs? Yet interpretability of them is rough.

We can build black boxes and exploit the behavior of what we see.

But we can’t always go to deeper and deeper layers of understanding.

QM is not a black boxes we built but one could perhaps say it’s a black box that we see.

If one does understand quantum mechanics well enough to use it, then one also understands that there are aspects of it we do not fully understand.

We understand part of it but not how it works.

Or we understand just enough to make things and instruments that only work on (and up to) the layer that we understand.

Ancient humans could build boats 5000 years ago and expand throughout the planet, but they didn't know about water being made up of hydrogen+oxygen, or the tides being caused by the moon, etc.

Their calculations served them on the layer they operated on.