Labs should make sure that the safety measures they apply to their powerful models prevent unacceptably bad outcomes, even if the AIs intentionally try to subvert those safety measures.
Share this post
The case for ensuring that powerful AIs are…
Share this post
Labs should make sure that the safety measures they apply to their powerful models prevent unacceptably bad outcomes, even if the AIs intentionally try to subvert those safety measures.