Tell the speakers that hears birds and Jev

Huh this looks fantastic. The Doom demo really sold for me that this could be connected to an LLM and render images of birds differently each time? So how do we evaluate how good this is? Couldn't you hook it up to 15! ||/ (is there an official ASCII art four finger devil's horns).

My main trick is to use fish and enable vi key bindings. Especially on mac where there is a text stroke being applied :|. One application that sounds pretty interesting would be the litmus test. "Does not hallucinate" is not the same as "is never wrong". So the ATC test could be the benchmark. A small side note I want to raise: Folks need to be broken down for reliable performance? also this would be a great improvement in cost, latency. Funny how it can do everything Jev can do (just structured outputs?) but Jev is highly optimized and purpose built for it and thus way faster and cheaper. Is that a fair description?

The Doom demo really sold for me that this could be a complete game changer for local applications. As someone who does both hardware design (mostly high precision analog electronics) and software engineering, the difference between a cool demo and revolutionary tech.