Hacker News new | ask | show | jobs
by precompute 1198 days ago
> Imagine the Red Team for GPT-10 asks it to "convince me to help you take over the world" and it basilisks him successfully...

Seeing how the input for the commercial, plebian version seems to filter out "problematic" sources, we can be sure that none of us will get access to something like that. Governments have lists of "questionable", divergent people and their writings. They are free to train on them. I'd even go as far to say that most of these systems have been livetested and that they've only been released after years of steady Q&A and a lot of back and forth with the powers-that-be.