I think Eliezer once wrote something about things becoming clearer when you think about how you would program a computer to do it, as opposed to e.g. just throwing some applause lights to a human. So, how specifically would you implement this kind of belief in a computer?
Also, should we go meta and say: “‘Rationality gives us a better understanding of the world, except when it does not’ is a good ideology, except when it is worse” et cetera?
What exactly would that actually mean? (Other than verbally shielding yourself from criticism by endless “but I said ‘except when not’”.) Suppose a person A believes “there is a 80% probability it will rain tomorrow”, but a person B believes “there is a 80% probability it will rain tomorrow, except if it is some different probability”. I have an idea about how A would bet about tomorrow’s weather, but how would B?
I think Eliezer once wrote something about things becoming clearer when you think about how you would program a computer to do it, as opposed to e.g. just throwing some applause lights to a human. So, how specifically would you implement this kind of belief in a computer?
First solve natural language...
No one has used eliezer’s technique much and there may be a reason for that.
“’Rationality gives us a better understanding of the world, except when it does not”
I provided this as an exaggerated example of how aiming for absolute truth can mean that you produce an ideology that is hard to explain. More realistically, someone would write something along the lines of, rationality gives us a better understanding of the world, except in cases a), b), c)… but if there are enough of these cases and these cases are complex enough, then in practise people round it off to “X is true, except when it is not”, ie. they don’t really understand what is going on as you’ve pointed out.
The point was that there are advantages of creating a self-conscious ideology that isn’t literally true, but has known flaws, such as it becoming much easier to actually explain so that people don’t end up being confused as above.
In other words, as far as I can tell, it doesn’t seem that your comment isn’t really responding to what I wrote.
I think Eliezer once wrote something about things becoming clearer when you think about how you would program a computer to do it, as opposed to e.g. just throwing some applause lights to a human. So, how specifically would you implement this kind of belief in a computer?
Also, should we go meta and say: “‘Rationality gives us a better understanding of the world, except when it does not’ is a good ideology, except when it is worse” et cetera?
What exactly would that actually mean? (Other than verbally shielding yourself from criticism by endless “but I said ‘except when not’”.) Suppose a person A believes “there is a 80% probability it will rain tomorrow”, but a person B believes “there is a 80% probability it will rain tomorrow, except if it is some different probability”. I have an idea about how A would bet about tomorrow’s weather, but how would B?
First solve natural language...
No one has used eliezer’s technique much and there may be a reason for that.
“’Rationality gives us a better understanding of the world, except when it does not”
I provided this as an exaggerated example of how aiming for absolute truth can mean that you produce an ideology that is hard to explain. More realistically, someone would write something along the lines of, rationality gives us a better understanding of the world, except in cases a), b), c)… but if there are enough of these cases and these cases are complex enough, then in practise people round it off to “X is true, except when it is not”, ie. they don’t really understand what is going on as you’ve pointed out.
The point was that there are advantages of creating a self-conscious ideology that isn’t literally true, but has known flaws, such as it becoming much easier to actually explain so that people don’t end up being confused as above.
In other words, as far as I can tell, it doesn’t seem that your comment isn’t really responding to what I wrote.