For any piece of information (expert statements, benchmarks, surveys, etc.) most good faith people agree on wether it makes doom more or less likely.
But we don’t agree on how much they should move our estimates, and there’s no good way of discussing that.
How to do better?
Certainly a thought provoking post! We try to think about the downsides of polarization and how to avoid them.
In this precise case do you think it’s a risk?
Thanks ! I uploaded the images to https://imgbb.com/ and uploaded them here from there.
Thanks for your post, I appreciate the improvement to your argument !
1- It isn’t clear to me why observing other forms of conscious intelligences leads to low interest in running non-me-simulations and only non-me-simulations. To me, there are other reasons to make simulations than those you highlited. I might concede that observing other forms of conscious intelligence might lessen motivation for creating full-scale simulations, but I think it would also reduce the need for me-simulations, for the same reasons.
2- Since there is a non-zero chance for you to be in an non-me-simulation or in reality, wouldn’t it still compell you to act altruistically, at least to some extent ? What are the probabilities you would assign to those events ?
Thanks for doing these, you have a rare gift
I look forward to your posts on AI every week!