They could allow AI PRs, but then have another AI PR reviewer reject them if they do not match the definitions for `to-the-point` `no-bullshit` commits.

▲

skeeter2020 an hour ago | parent | next [-]

Please provide 3 examples where layering on MORE of the offending technology has solved the problem. Spam? Malware & Viruses? Customer Service? Hiring & Recruitment?

▲

mort96 5 hours ago | parent | prev [-]

And who pays for the (likely significant, and controllable by everyone) tokens such a system would use?

▲

julianlam 4 hours ago | parent [-]

A small 4-9B model would be able to run cheaply for this sort of work.

▲

krainboltgreene 4 hours ago | parent [-]

What question do you think you're answering?

▲

Cpoll 3 hours ago | parent [-]

The Godot Foundation pays for it if it furthers their mission.

	▲	mort96 3 hours ago \| parent [-]
		Does it?