Many advocate for making AI “corrigible” or “steerable”. In its purest form, this makes AI a mere vessel for the will of the user.
Depends on definition of ‘user’, but this is locally quite invalid: “corrigible tO wHoM??!” to paraphrase a commonly uttered question which is here relevant!
(I’m pretty sure you get this, based on the rest of the post, but this is a flattening of the ‘corrigible’ term of art.)
Depends on definition of ‘user’, but this is locally quite invalid: “corrigible tO wHoM??!” to paraphrase a commonly uttered question which is here relevant!
(I’m pretty sure you get this, based on the rest of the post, but this is a flattening of the ‘corrigible’ term of art.)
Yep, good catch! In this case, I meant to the user.