> "Don't worry if our adversary develops nuclear weapons and we won't - it's OK we'll just use theirs"
Beneath this comment is hidden a truth that there is AI which can be used beneficially, AI which can be used detrimentally, AI which can be weaponized in warfare, and AI which can be used defensively in warfare. Discussions about policy and regulation should differentiate these, but also consider implications of how this technology is developed and for what purpose it could be employed.
We should definitely be developing AI to combat AI as it will most certainly be weaponized against us with greater frequency in the near future.
Yes and I think it's broader than that. For example, if a country uses AI to (say) optimize their education or their economy - they will "run away" from us. Rather than enabling us to use that technology too (why would they, even for money) they can just wait until their advantage is insurmountable.
So it's not just pure warfare systems that are risky for us but everything.
Beneath this comment is hidden a truth that there is AI which can be used beneficially, AI which can be used detrimentally, AI which can be weaponized in warfare, and AI which can be used defensively in warfare. Discussions about policy and regulation should differentiate these, but also consider implications of how this technology is developed and for what purpose it could be employed.
We should definitely be developing AI to combat AI as it will most certainly be weaponized against us with greater frequency in the near future.