De La Rosa asks what procedures exist for those risks
De La Rosa asks what procedures are in place if bioterrorism or rogue system risks arise; Castillo-Madrid describes regular training, pre-training, post-training, fine-tuning, adversarial stress testing, and safety protocols scaling with capabilities.
What are some of the procedures in place if there is that type of risk?
To add, SpaceX SI engages in regular trainings throughout model development, and that includes pre-training, post-training, fine-tuning, and adversarial stress testing.
And we do that, and it's not something that stops once the model is released.
We understand that it's important to make sure our safety protocols are scaling with our capabilities,
and the public can take great confidence in that we're testing the testing that occurs before models are released and the safeguard stacks that are surrounding model deployments are ongoingly or we ongoingly
look for for any issues and make sure that we're closing any gaps that need stronger protections