For example, someone who was completely colorblind from birth could never understand what it felt like to see the color green, no matter how much neuroscience that person knew, i.e., you could never convey the sensation of "green" through a layout of a connectome or listing wavelengths of light.
I didn't have a problem with 1 or 2 but 3 and 4 were the big problems. Though I didn't downvote because it was already well negative at that point. Saying AI is software is an assertion but its not meaningful. Are you saying software that prints 'hello world' is intelligent? From some of your previous comments I gather you are interested in how software, the user, the designer and other software interact in some way but there was none of that in the post. Its as if Eliezer had said 'rationality IS winning IS rationality' as the entirety of the sequences.
"Again and again, I’ve undergone the humbling experience of first lamenting how badly something sucks, then only much later having the crucial insight that its not sucking wouldn’t have been a Nash equilibrium." --Scott Aaronson
A Christian proverb says: “The Church is not a country club for saints, but a hospital for sinners”. Likewise, the rationalist community is not an ivory tower for people with no biases or strong emotional reactions, it’s a dojo for people learning to resist them.
I find it takes a great deal of luminosity in order to be honest with someone. If I am in a bad mood, I might feel that its my honest opinion that they are annoying when in fact what is going on in my brain has nothing to do with their actions. I might have been able to like the play in other circumstances, but was having a bad day so flaws I might have been otherwise able to overlook were magnified in my mind. etc.
This is my main fear with radical honesty, since it seems to promote thinking that negative thoughts are true just because they are negative....
This is my main fear with radical honesty, since it seems to promote thinking that negative thoughts are true just because they are negative. The reasoning going 'I would not say this if I were being polite, but I am thinking it, therefore it is true' without realizing that your brain can make your thoughts be more negative from the truth just as easily as it can make them more positive than the truth.
My own (very limited) observation of trying to be radically honest has been that until I first say (or at least admit to myself) the reaction of annoyance...
If I am honest without accuracy... if I am proud to report my results of my reasoning as they are, but my actual reasoning is sloppy... then I shouldn't congratulate myself for giving precise info, because the info was not precise; I simply removed one source of imprecision, but ignored another.
Saying "you are annoying" feels like an extremely honest thing, and I may be motivated to stop there.
However, saying "sorry, I'm in a bad mood today; I think it's likely that on a different day I would appreciate what you are trying to do, but today i...
This made me think; I may have some luminosity privilege that needs checking...
he puts 2.72 on the table, and you put 13.28 on the table.
I'm confused...if the prediction does not come true (which you estimated as being 33 percent likely) you only gain $2.72? and if the most probable outcome does come true you lose 13.28?
An always open mind never closes on anything. There is a time to confess your ignorance and a time to relinquish your ignorance and all that...
Well, yes, obviously the classical paperclipper doesn't have any qualia, but I was replying to a comment wherein it was argued that any agent on discovering the pain-of-torture qualia in another agent would revise its own utility function in order to prevent torture from happening. It seems to me that this argument proves too much in that if it were true then if I discovered an agent with paperclips-are-wonderful qualia and I "fully understood" those experiences I would likewise be compelled to create paperclips.
By signing up for cryonics you help make cryonics more normal and less expensive, encouraging others to save their own lives. I believe there was a post where someone said they signed up for cryonics so that they wouldn't have to answer the "why aren't you signed up then?" crowd when trying to convince other people to do so.
Anyone who is isn't profoundly disturbed by torture, for instance, or by agony so bad one would end the world to stop the horror, simply hasn't understood it.
Similarly, anyone who doesn't want to maximize paperclips simply hasn't understood the ineffable appeal of paperclipping.
Taking this post in the way it was intended i.e. 'are there any reasons why such a policy would make people more likely to attribute violent intent to LW' I can think of one:
The fact that this policy is seen as necessary could imply that LW has a particular problem with members advocating violence. Basically, I could envision the one as saying: 'LW members advocate violence so often that they had to institute a specific policy just to avoid looking bad to the outside world'
And, of course, statements like 'if a proposed conspiratorial crime were in fact good you shouldn't talk about it on the internet' make for good out-of-context excerpts.
I feel this should not be in featured posts, as amusing as it was at the time