because the world is way scarier than I thought it was.

I would recommend taking some time to double-check this before doing something hard to undo.

Keep in mind Eliezer's mistake with the basilisk. Based on a quick analysis, he decided the best course of action was to stop thinking about it and encourage others to do likewise. The problem (assuming my model of him is correct) is that since he stopped thinking about it, he didn't realize his initial analysis was wrong. In fact as far as I know, he still hasn't realized it.

I would recommend taking some time to double-check this before doing something hard to undo.

How much time do you recommend? The thing is I already didn't like credibility, so this new action isn't a drastic change, just a quickening.

he didn't realize his initial analysis was wrong. In fact as far as I know, he still hasn't realized it.

I'm actually not sure what you have in mind here. We might want to discuss this via PM. (Obviously I'm already familiar with the basilisk and the class of problems it's representative of.)

This post is for sacrificing my credibility!

by Will_Newsome 1 min read2nd Jun 2012347 comments

-30


Thank you for your cooperation and understanding. Don't worry, there won't be future posts like this, so you don't have to delete my LessWrong account, and anyway I could make another, and another.

But since you've dared to read this far:

Credibility. Should you maximize it, or minimize it? Have I made an error?

Discuss.

Don't be shallow, don't just consider the obvious points. Consider that I've thought about this for many, many hours, and that you don't have any privileged information. Whence our disagreement, if one exists?