I agree that guarding against nation state cyberattacks is extremely hard, but disagree that this is particularly relevant. The proportion of capability-pushing research that travels between ML researchers through espionage is quite low.
Edit: Obviously misaligned AIs should not be leaked.
I agree that guarding against nation state cyberattacks is extremely hard, but disagree that this is particularly relevant. The proportion of capability-pushing research that travels between ML researchers through espionage is quite low.
Edit: Obviously misaligned AIs should not be leaked.