[xraystyle]

That's the thing though, is that it's not hard to make a good antenna for a single frequency. We already know exactly how to do that. And when we're talking transmission and reception of radio, tiny incremental gains that might be eked out through some wacky design generally don't move the needle very much.

I can talk to the astronauts on the ISS on 2 meters with an antenna I can make out of a PVC pipe and a metal measuring tape using a 5-watt transmitter. Improving that design by 2% doesn't really mean anything useful in this context.

It would usually be vastly cheaper and easier to just increase the transmit power. Or sometimes it's the available power that's the limiting factor, and a 2% increase to the antenna isn't going to matter.

Point is, trying to chase tiny gains in one dimension or another over a thoroughly tested and well-understood antenna design is kind of a waste of time outside of an academic, beard-scratching context.

[quesera]

Well, the speculation is that an AI could iterate through a zillion novel and mostly-garbage designs to discover something unexpected with a higher gain than known designs.

There's a percent efficiency/gain improvement that exceeds the cost-performance ratio of simply increasing power -- boiling down to the usual capex vs opex argument.

I can't make an intelligent guess on the likelihood of that discovery.