I was responding sardonically to their statement: “More broadly, I am struggling to see what evidence you have for why current alignment frameworks (among other things) would fail to transfer to more capable models.” I maybe deserve the “too sneering” or “too combative” react for it.
The statement seems indicative of the view that companies should be allowed to push ahead with whatever they are doing unless someone can prove it is unsafe and harmful. I think a much healthier view for society to hold is that companies should NOT be allowed to push ahead with whatever they are doing unless someone can prove that it IS safe and NOT harmful.
Yup, that would be a healthier view for society to hold. Sadly in pretty much any field that I’m aware of, companies are allowed to push ahead until accidents happen and until it’s proven that it’s unsafe.
We’ll need to find some way of overcoming that default since we’ll only get 1 real shot atn superintelligence alignment.
Isn’t he saying the opposite?
I was responding sardonically to their statement: “More broadly, I am struggling to see what evidence you have for why current alignment frameworks (among other things) would fail to transfer to more capable models.” I maybe deserve the “too sneering” or “too combative” react for it.
The statement seems indicative of the view that companies should be allowed to push ahead with whatever they are doing unless someone can prove it is unsafe and harmful. I think a much healthier view for society to hold is that companies should NOT be allowed to push ahead with whatever they are doing unless someone can prove that it IS safe and NOT harmful.
Yup, that would be a healthier view for society to hold. Sadly in pretty much any field that I’m aware of, companies are allowed to push ahead until accidents happen and until it’s proven that it’s unsafe.
We’ll need to find some way of overcoming that default since we’ll only get 1 real shot atn superintelligence alignment.