Hacker Read top | best | new | newcomments | leaders | about | bookmarklet login

In that case there are two attractors - one towards the Golden Gate Bridge and one towards the harmless, helpful, honest assistant persona. Techniques as such probably get weirder results with model scale but no reason to think they get wiped out.


view as:

What if the Golden Gate Bridge is Main Kampf or something like that?

Legal | privacy