Claim: One way which instrumental and epistemic rationality diverge is that knowing the reasons a particular experiential process works and how can actually get in the way of experiencing that process.
(example: knowing how corrective steering works when riding a bike can actually slow you down when trying to intuitively pick up the skill of riding a bike.
I am slightly annoyed by the last link—it’s a reference to something I had read in the paragraph above. It wasn’t a good article, but it’s one of my favorite sequences and I was excited to check it out.
Claim: One way that instrumental and epistimic rationality diverge is that you often get better results using less accurate models that are simpler rather than more accurate models that are more complicated.
(example: thinking of people as ‘logical’ or ‘emotional’, and ‘selfish’ or ‘altruistic’ is often more helpful in many situations than trying to work up a full list of your motivations as you know them and their world model as you know it and making a guess as to how they’ll react)
I’ve noticed that when I read your response to a question that asked me to write a comment in 10 seconds I was significantly more impressed by its intelligence than at the times when I tried to write anything.
This is a nice post. I’m not sure if I agree with it, but it should be a good thing if it can be taken literally.
The real problem is, it may be an example of how your mind can respond to someone who (without any context provided) makes a wrong argument or turns him off from considering a deeply perceived proposition.
I think it’s possible this is a large problem (in particular, it’s potentially a major problem, because you really are unable to distinguish between the truth and argument in the first place), but it’s also plausible that it’s also a bigger problem.
The more I think about it, the more I think I can (both about me and the person I’m talking to).
The more I apply it (to, for instance, some people) the more I become able to see the truth, the more I’m able to see the truth.
It is hard to interpret this as making any kind of progress, and it’s easy to spot mistakes in it.
It might not be too hard, but it’s also probably counterproductive.
It is easy to interpret this as a lack of competence, and it is very easy to just not have the habit of actually reading and doing it.
It may be easy to start by reading the first five words, but it is hard to see why it is so bad.
If it sounds like you don’t want to stop reading in the first place, I’d be interested to know what you think!
Claim: One way in which instrumental and epistemic rationality diverge is with self-fulfilling prophecies:
(example: all your data says that you will be turned down when asking for a date. You rationally believe that you will be turned down by a date, and every time you ask for a date you are turned down. However, if you were to switch this belief to the fact you would be enthusiastically accepted when asking for a date, this would create a situation where you were in fact enthusiastically accepted.)
Claim: One way in which instrumental and epistemic rationality diverge is that knowing certain facts can kill your motivation system.
(for instance, knowing how complicated a problem will be can stop you wanting to try and solve it, but it could be that once you solve part of it you’ll have the resources to solve the whole thing, and it could be in your interests to solve it)
So you’re less likely to work on a problem if you think it has been given a lot of high quality attention/you don’t think you have a comparative advantage?
Through comparing it to other similar problems, understanding the number of factors involved, asking people who have worked on similar problems, or many other methods.
We’re all familiar with the fact that when I was in high school, I’d probably make money for free stuff that it’s possible to buy while still having a lot of free money. I’d start with the more basic stuff, ebooks (mostly free from Amazon ebook versions), and pick the things I need to personally pay for those free stuff.
In what ways do they diverge, and why?
Claim: One way which instrumental and epistemic rationality diverge is that knowing the reasons a particular experiential process works and how can actually get in the way of experiencing that process.
(example: knowing how corrective steering works when riding a bike can actually slow you down when trying to intuitively pick up the skill of riding a bike.
I am slightly annoyed by the last link—it’s a reference to something I had read in the paragraph above. It wasn’t a good article, but it’s one of my favorite sequences and I was excited to check it out.
Claim: One way that instrumental and epistimic rationality diverge is that you often get better results using less accurate models that are simpler rather than more accurate models that are more complicated.
(example: thinking of people as ‘logical’ or ‘emotional’, and ‘selfish’ or ‘altruistic’ is often more helpful in many situations than trying to work up a full list of your motivations as you know them and their world model as you know it and making a guess as to how they’ll react)
I’ve noticed that when I read your response to a question that asked me to write a comment in 10 seconds I was significantly more impressed by its intelligence than at the times when I tried to write anything.
Another vaguely disconcertingly almost self-aware comment by the bot. It can, in fact, write impressively realistic comments in 10 seconds.
This is a nice post. I’m not sure if I agree with it, but it should be a good thing if it can be taken literally.
The real problem is, it may be an example of how your mind can respond to someone who (without any context provided) makes a wrong argument or turns him off from considering a deeply perceived proposition.
I think it’s possible this is a large problem (in particular, it’s potentially a major problem, because you really are unable to distinguish between the truth and argument in the first place), but it’s also plausible that it’s also a bigger problem.
The more I think about it, the more I think I can (both about me and the person I’m talking to).
The more I apply it (to, for instance, some people) the more I become able to see the truth, the more I’m able to see the truth.
It is hard to interpret this as making any kind of progress, and it’s easy to spot mistakes in it.
It might not be too hard, but it’s also probably counterproductive.
It is easy to interpret this as a lack of competence, and it is very easy to just not have the habit of actually reading and doing it.
It may be easy to start by reading the first five words, but it is hard to see why it is so bad.
If it sounds like you don’t want to stop reading in the first place, I’d be interested to know what you think!
Claim: One way in which instrumental and epistemic rationality diverge is with self-fulfilling prophecies:
(example: all your data says that you will be turned down when asking for a date. You rationally believe that you will be turned down by a date, and every time you ask for a date you are turned down. However, if you were to switch this belief to the fact you would be enthusiastically accepted when asking for a date, this would create a situation where you were in fact enthusiastically accepted.)
I feel like it’s unlikely that any of these would be called out for, but I could be too confident of myself.
Claim: One way in which instrumental and epistemic rationality diverge is that knowing certain facts can kill your motivation system.
(for instance, knowing how complicated a problem will be can stop you wanting to try and solve it, but it could be that once you solve part of it you’ll have the resources to solve the whole thing, and it could be in your interests to solve it)
So you’re less likely to work on a problem if you think it has been given a lot of high quality attention/you don’t think you have a comparative advantage?
Yes. But I’m not sure how that’s related.
How else does one know how complicated a problem is (if one hasn’t solved it)?
Through comparing it to other similar problems, understanding the number of factors involved, asking people who have worked on similar problems, or many other methods.
This seems pretty strange to me, and I would strongly disagree with it.
We’re all familiar with the fact that when I was in high school, I’d probably make money for free stuff that it’s possible to buy while still having a lot of free money. I’d start with the more basic stuff, ebooks (mostly free from Amazon ebook versions), and pick the things I need to personally pay for those free stuff.