At one point (working off memory here), Sam Altman (leader of OpenAI) didn’t quite agree with the orthogonality thesis. After some discussion and emailing with someone on the Eleuther discord (iirc), he shifted to agree with it more fully. I think.
This ties into my overall point of “some of this might be adversarial, but first let’s see if it’s just straight-up neglected along some vector we haven’t looked much at yet”.
At one point (working off memory here), Sam Altman (leader of OpenAI) didn’t quite agree with the orthogonality thesis. After some discussion and emailing with someone on the Eleuther discord (iirc), he shifted to agree with it more fully. I think.
This ties into my overall point of “some of this might be adversarial, but first let’s see if it’s just straight-up neglected along some vector we haven’t looked much at yet”.