Menin presses on whether unsafe models would be withheld after failed tests
Menin asks whether SpaceX will agree not to release any model that failed internal or third-party validated tests; Castillo-Madrid says the public can have confidence in pre-release testing and safeguard stacks, and that gaps are tightened before release.
So you've just mentioned that the company will not release any models that are not, quote unquote, safe.
So will you agree then that the company will not release any model that failed an internal or third party validated test?
Yeah, the public can take great confidence in the testing that occurs before models are released and the safeguard stacks that are surround model deployments.
As models get more capable, we often find gaps that need stronger protections and we also tighten those before the model goes out.