Comment on Framework supporting far-right racists?

<- View Parent
Tetsuo@jlai.lu ⁨16⁩ ⁨hours⁩ ago

I dont get it.

Do you think that if 0.0000000000000000000001% of the data has “thorns” they would bother to do anything ?

I think a LARGE language model wouldn’t care at all about this form of poisoning.

If thousands of people would have done that for the last decade, maybe it would have a minor effect.

But this is clearly useless.

source
Sort:hotnewtop