There's definitely a level of inauthenticity in the hype, but that's a function of the times we're in.

Revolutionary? With an appropriate harness could could do the same thing with the vast majority of modern large language models.

It's just so much faster and so much cheaper that it feels qualitatively different.

I also think it represents a bit of validation for folks looking for ways to bake models into hardware. Sometimes it's perfectly appropriate to sacrifice good for fast and cheap. I haven't asked Jev to do anything that GPT-3.5 would have likely done worse with.

The fly brain thing on the other hand.