I haven’t been specific in what I said. There actually have been some posts that introduced me to new concepts and allowed me to feel more satisfied to believe certain things. Only because of LW I was able to compile this curriculum. Although there are many more insightful and novel comments in my opinion than there are posts. I don’t want to appear arrogant here or downplay the value of Less Wrong. I actually believe it is one of the most important resources. I just haven’t read enough of LW yet to notice any capital contradictions. That also means that there might be great insights I haven’t come across yet. I also don’t think that most ideas here need much support (the top-ranked post seems to be an outlier). But take a look at some popular posts, where do you disagree or what have they taught you that you didn’t already come up with on your own? Take for example the Ugh fields. Someone like me who managed to abandon religion without any help on his own reads that post, agrees wholeheartedly and upvotes it. But has it helped me? No, I’m rather a person that naturally takes this attitude too serious, I consciously overthink things until I completely leave near-mode and operate in far-mode only. I thought your post on self-fulfilling correlations was awesome. But there was no novel insight for me in it either. I know lots of people who should read your post and would benefit from it a lot. But such people won’t read it. People like me who visit a psychologist because they know they need help won’t be surprised by the movie Contact when Jodie Foster admits it could have all been some illusion. People like me are naturally aware that they could be dreaming. Doubt and the possibility of self-delusion are fundamental premises. But the people who’d really have to go to a psychologist, or read Less Wrong, believe they are perfectly normal or don’t need to be told anything.
What I’m trying to say is that if Less Wrong wants to change the world rather than being a place where hyper-rationalists can collectively pat their back, you need to think about how to reach the people who need to know about it. And you need feedback, you have to figure out why people like Ben Goertzel fail to share some conclusions being made here and update accordingly.
Were there ever any references identifying the Scary Idea as an official SIAI belief?
I think that—if they comment at all—they would come back with something like:
OK—so you don’t think that unconstrained machine intelligence is “highly likely” to automatically DESTROY ALL LIFE AS WE KNOW IT. So: what do you think the chances of that happening are?!?
Does Eliezer believe that working on friendly AI and supporting friendly AI research is the most important and most rational way to positively influence the future of humanity? If he thinks so, then is it reasonable to suspect that his rationale for starting to write on matters of rationality was to plead his case for friendly AI research and convince other people that it is indeed the most effective way to help humankind? If not, what was his reason to start blogging on Overcoming Bias and Less Wrong? Why has he spent so much time helping people to become less wrong rather than working directly on friendly AI? How can you be less wrong and still doubt that you should support friendly AI research?
I still suspect that everything he does is a means to an end. I’m also the opinion that if one reads all of Less Wrong and is afterwards (in the case one wants to survive and benefit humanity) still unable to conclude that the best way to do so is by supporting the SIAI, then either one did not understand due to a lack of intelligence or Less Wrong failed to convey its most important message. Therefore you should listen to the people who have read Less Wrong and disagree. You should also try to reach the people who haven’t read Less Wrong but should read it because they are in a position that makes it necessary for them to understand the issues in question.
Well, I tend to think that that working on and supporting machine intelligence research is probably the most important way to positively influence the future of civilisation. The issue of what we want the machines to do is a part of the project.
So, such beliefs don’t seem particularly “far out”—to me.
FWIW, Yudkowsky describes his motivation in writing about rationality here:
I haven’t been specific in what I said. There actually have been some posts that introduced me to new concepts and allowed me to feel more satisfied to believe certain things. Only because of LW I was able to compile this curriculum. Although there are many more insightful and novel comments in my opinion than there are posts. I don’t want to appear arrogant here or downplay the value of Less Wrong. I actually believe it is one of the most important resources. I just haven’t read enough of LW yet to notice any capital contradictions. That also means that there might be great insights I haven’t come across yet. I also don’t think that most ideas here need much support (the top-ranked post seems to be an outlier). But take a look at some popular posts, where do you disagree or what have they taught you that you didn’t already come up with on your own? Take for example the Ugh fields. Someone like me who managed to abandon religion without any help on his own reads that post, agrees wholeheartedly and upvotes it. But has it helped me? No, I’m rather a person that naturally takes this attitude too serious, I consciously overthink things until I completely leave near-mode and operate in far-mode only. I thought your post on self-fulfilling correlations was awesome. But there was no novel insight for me in it either. I know lots of people who should read your post and would benefit from it a lot. But such people won’t read it. People like me who visit a psychologist because they know they need help won’t be surprised by the movie Contact when Jodie Foster admits it could have all been some illusion. People like me are naturally aware that they could be dreaming. Doubt and the possibility of self-delusion are fundamental premises. But the people who’d really have to go to a psychologist, or read Less Wrong, believe they are perfectly normal or don’t need to be told anything.
What I’m trying to say is that if Less Wrong wants to change the world rather than being a place where hyper-rationalists can collectively pat their back, you need to think about how to reach the people who need to know about it. And you need feedback, you have to figure out why people like Ben Goertzel fail to share some conclusions being made here and update accordingly.
Were there ever any references identifying the Scary Idea as an official SIAI belief?
I think that—if they comment at all—they would come back with something like:
Does Eliezer believe that working on friendly AI and supporting friendly AI research is the most important and most rational way to positively influence the future of humanity? If he thinks so, then is it reasonable to suspect that his rationale for starting to write on matters of rationality was to plead his case for friendly AI research and convince other people that it is indeed the most effective way to help humankind? If not, what was his reason to start blogging on Overcoming Bias and Less Wrong? Why has he spent so much time helping people to become less wrong rather than working directly on friendly AI? How can you be less wrong and still doubt that you should support friendly AI research?
I still suspect that everything he does is a means to an end. I’m also the opinion that if one reads all of Less Wrong and is afterwards (in the case one wants to survive and benefit humanity) still unable to conclude that the best way to do so is by supporting the SIAI, then either one did not understand due to a lack of intelligence or Less Wrong failed to convey its most important message. Therefore you should listen to the people who have read Less Wrong and disagree. You should also try to reach the people who haven’t read Less Wrong but should read it because they are in a position that makes it necessary for them to understand the issues in question.
Well, I tend to think that that working on and supporting machine intelligence research is probably the most important way to positively influence the future of civilisation. The issue of what we want the machines to do is a part of the project.
So, such beliefs don’t seem particularly “far out”—to me.
FWIW, Yudkowsky describes his motivation in writing about rationality here:
http://lesswrong.com/lw/66/rationality_common_interest_of_many_causes/