@ohabryka @sebkrier "Clearly" we should note that @sebkrier didn't actually say what his plan is in this post. Don't put words in his mouth
Oliver Habryka@ohabrykaNo, this is literally not what the result says! Data filtering does not have a big effect! Upweighing positive stories has a big effect. Also, really, your plan for controlling superintelligence is so hyperstition a meme that "alignment is easy"? Clearly you can't be serious about this.
@robertwiblin You can also see the defensiveness in @slatestarcodex's https://blog.aifutures.org/p/against-misalignment-as-self-fulfilling. It doesn't make sense.
Arguments weak, claims too strong. I told them not to post in that form, gave counterevidence, and then http://alignmentpretraining.ai indeed debunked important claims in the post
Alex Turner@Turn_Trout@robertwiblin Yeah but it's in fact true that self-fulfilling misalignment is a negative impact of LW discourse. That doesn't mean we should ban the discourse or that it was overall bad to discuss. But the negative externality is real