We do separately measure the model capabilities as a way of bounding how much harm could be caused by deliberate ‘misuse’, which would include instructing a model to cause harm.
What we’re interested in here is how likely it would be for a model to engage in this set of behaviour when we are making a best-effort attempt to get useful work out of it.
We do separately measure the model capabilities as a way of bounding how much harm could be caused by deliberate ‘misuse’, which would include instructing a model to cause harm.
What we’re interested in here is how likely it would be for a model to engage in this set of behaviour when we are making a best-effort attempt to get useful work out of it.