The authors argue that generative AI introduces a new class of alignment risks because interaction itself becomes a mechanism of influence. Humans adapt their behavior in response to AI outputs, ...
Horizontal lines run left to right, parallel to the horizon, with slope 0 and equation y = k. Vertical lines run top to bottom, perpendicular to the horizon, with undefined slope and equation x = k.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback