Another possible best practice for evals: use human+AI rather than [edit: just] AI alone. Many threat models involve human+AI and sometimes human+AI is substantially stronger than human alone and AI alone.
You mean “in addition to”, right? Knowing what the AI alone is capable of doing is quite an important part of what evals are about, so keeping it there seems crucial.
Another possible best practice for evals: use human+AI rather than [edit: just] AI alone. Many threat models involve human+AI and sometimes human+AI is substantially stronger than human alone and AI alone.
You mean “in addition to”, right? Knowing what the AI alone is capable of doing is quite an important part of what evals are about, so keeping it there seems crucial.