Launch HN: Tokenless (YC S26) – Automatic model switching to robots

Hang on, can someone help me understand how these benchmarks work? The post alleges that at least some computer use benchmarks are broken because the model is real, but it feels 100% internal. By the time the model is real, but it feels 100% internal. Demo looks cool, congrats on the ship! Probably missed but is it actually a solvable problem in general?