pgn

reminds me of the faux "new internet" pitch from silicon valley. in tone at least.

That makes sense -- these are details that would be good to have in the methodology :)

Would be interested on the results from running a similar experiment with more powerful models, though that's more of a curiosity thing than anything lol

what was the selection for the teams? random per round? how does it play against people in ladder?

> It's likely that this would now require actually reverse engineering the circuit subcomponents, but that is an entire rabbit hole I do not have time to go down at this point.

This is the route I ended up going! I posted my own writeup here: https://pradyun.net/blog/reverse_engineering.html