I am more optimistic that we can get such empirical evidence for at least the most important parts of the AI risk case, like deceptive alignment, and here’s one reason as comment on offer:
Can you elaborate on what you were pointing to in the linked example? The thread specifically I’ve seen a few people mention recently but I seem to be missing the conclusion they’re drawing from it.
It sounds as though you’re imagining that we can proliferate the one case in which we caught the AI into many cases which can be well understood as independent (rather than basically just being small variations).
and this comment, which talks about proliferating cases where 1 AI schemes into multiple instances to get more evidence:
Can you elaborate on what you were pointing to in the linked example? The thread specifically I’ve seen a few people mention recently but I seem to be missing the conclusion they’re drawing from it.
I was pointing to this quote:
and this comment, which talks about proliferating cases where 1 AI schemes into multiple instances to get more evidence:
https://www.lesswrong.com/posts/YTZAmJKydD5hdRSeG/#BkdBD5psSFyMaeesS