Because that's impossible. Any "robot" that can generate code must be trained on massive amounts of code, most of which is open source.

And how are you supposed to guarantee equivalent functionality by analyzing "README files, API docs, and type definitions"?

Nolski an hour ago | parent | next [-]

It's described on the web page but it's by having 2 agents. One has access to the code and one doesn't.

	▲	fmbb an hour ago \| parent [-]
		Are they the same model? Not that it matters, I just think the joke is more fun if they are different.

dymk 2 hours ago | parent | prev [-]

The joke is that you don’t.