I’m also announcing this year’s first debate week! We’ll be discussing whether, on the margin, we should put more effort into reducing the chances of avoiding human extinction or increasing the value of futures where we survive.
Nice! A couple of thoughts:
1.
In addition to soliciting new posts for the debate week, consider ‘classic repost’-ing relevant old posts, especially ones that haven’t been discussed on the Forum before?
Alongside the debate statement voting, I think it could be very cool to let users create and post their own distribution over {great, fine, non-, bad, hellish} futures,[2] in line with the following diagram. You could then aggregate[3] users’ distributions and display a wisdom-of-the-EA-Forum-crowd prediction for the future:
Although a mean aggregation would be simplest, a better aggregation (in my view) would be to take the median user’s percentage within each of {great, fine, non-, bad, hellish}, and then normalize so that the five aggregate percentages add up to 100. (And you could optionally weight users’ distributions/predictions in line with their karma / strong-upvote power.)
(For context, the Metaculus forecasting platform’s ‘community prediction’ aggregation is a weighted median.)
Nice! A couple of thoughts:
1.
In addition to soliciting new posts for the debate week, consider ‘classic repost’-ing relevant old posts, especially ones that haven’t been discussed on the Forum before?
Tomasik’s ‘Risks of astronomical future suffering’ comes to mind, as well as Assadi’s ‘Will humanity choose its future?’ and Anthis’s ‘The future might not be so great’.[1]
2.
Alongside the debate statement voting, I think it could be very cool to let users create and post their own distribution over {great, fine, non-, bad, hellish} futures,[2] in line with the following diagram. You could then aggregate[3] users’ distributions and display a wisdom-of-the-EA-Forum-crowd prediction for the future:
This is, of course, not an endorsement of Anthis’s former conduct.
On the user end, this would just mean entering five percentages (which add up to 100).
Although a mean aggregation would be simplest, a better aggregation (in my view) would be to take the median user’s percentage within each of {great, fine, non-, bad, hellish}, and then normalize so that the five aggregate percentages add up to 100. (And you could optionally weight users’ distributions/predictions in line with their karma / strong-upvote power.)
(For context, the Metaculus forecasting platform’s ‘community prediction’ aggregation is a weighted median.)