ensuring that these experiments are as efficient and safe as possible
Is “safe” here meant in the sense of “not accelerating risks from AI,” or in the sense of “difficult to steal” (i.e. secure)?
A bit of both—but you’re right, I primarily meant “secure” (as I expect this is where engineers have something specific to contribute).
Is “safe” here meant in the sense of “not accelerating risks from AI,” or in the sense of “difficult to steal” (i.e. secure)?
A bit of both—but you’re right, I primarily meant “secure” (as I expect this is where engineers have something specific to contribute).