wedrifid comments on [LINK] Another "LessWrongers are crazy" article - this time on Slate - Less Wrong Discussion
You are viewing a comment permalink. View the original post to see all comments and the full post content.
You are viewing a comment permalink. View the original post to see all comments and the full post content.
Comments (129)
The basilisk get's more compliance from the believers when he puts the innocents into heaven then when he puts them into hell. Also the debate is not about an UFAI but a FAI that optimizes the utility function of general welfare with TDT.
This is also the point, where you might think about how Eliezer's censorship had an effect. His censuring did lead you and Viliam_Bur to have an understanding of the issue where you think it's about an UFAI.
This is at best not clear. It depends on the specific nature of the insanity in the compliant. Note that brutally disincentivizing evangelism has... instrumental downsides.
Don't be misled by the loose relationship with Pascal's Wager. This isn't about belief, it is about decisions (and counterfactual decisions).
The use of the term uFAI is deliberate, and correct. We don't need to define a torture-terrorist as Friendly just because of some sloppy utilitarian reasoning. Moreover, any actual risk from the scenario comes from AGI creators (or influencers) that make this assumption. That's the only thing that can cause the torture to happen.
You are overconfident in your mind reading skills. I was one of the few people who were familiar enough with the subject matter at the time when Roko was writing his (typically fascinating) posts that I categorised the agent as a plausible not-friendly AGI immediately, the scenario as an interesting twist on acausal extortion then went straight to thinking about the actual content of the post, which was about a new means of cooperation.