Philosophy, education, literary studies, computer game design.
Astor
The team is great. Thank you very much!
Thank you for organizing this program. I really enjoyed the book reviews. Even though I am still a bit shy in commenting and using votes, these posts encouraged me to consider writing something myself in the future.
I thought a solved alignment problem would implicate a constant process of changing the values of the AI in regard to the most recent human values. So if something does not lead to the expected terminal goals of the human (such as enjoyable emotions), then the human can indicate that outcome to the AI and the AI would adjust its own goals accordingly.
It’s always puzzling me why this is so hard to accept for me. Maybe one aspect could be that work relationships force you to present yourself as best as possible to your employer. And this leads to situations in which you try to signal competence instead of uncertainty, even to yourself.
Trying to build your own productivity tools is also very helpful in understanding why you have difficulties in the first place because you reflect upon them while designing your feature set. I really appreciate this post for reminding me of the joy of programming your own solutions.
I don’t know if Wittgenstein was the originator of this concept, but he seems to have made it more prominent.
I suppose the pragmatic maxim is also related to this. I always wondered, if Wittgenstein read Peirce’s argument in regard to metaphysics.
I really like your review, but I have to admit that I do not like Wittgenstein’s concepts. I am simply not sure how to use them in any meaningful way. Unfortunately this has not changed after reading your text.
For example, for me, J. L. Austin explained the whole “language as use” philosophy way better in “How To Do Things With Words” and in most cases I refer to the concept of Sprachdynamik as the principle theory of language change and development, rather than mentioning “language-games”. Language-games reinforce the elusiveness of concepts, words and language as a whole. But if you want to use language to do something you have to hold onto at least some meanings.
This contrasts your last section and I do not know how you arrived at your conclusions. Your arguments seem to refer to the elusiveness as a possible building block for ones own definitions. But this seems to be exactly what analytical philosophers try to achieve, or not? They try to find the best possible definition which can be applied to hopefully all but practically most situations. The mentioned difference between conceptual engineering and analysis does not convince me.
Family resemblances also seem to be only useful in denying problems: I cannot find a simple definition for some widely used word therefore it must be a family resemblance and not further be investigated. I am not so sure.
In his argument against private languages I cannot even understand what he means by the word language. His example for a private language is something that is fully untranslatable like the sensations of emotions. But what exactly does it mean to speak of sensations as a private language? What?
This is really unsatisfying. So for me, Wittgenstein is just one of the lesser concept manufacturers, who had luck in getting referenced over and over again. But don’t take my word on this! Maybe other people have more luck with these concepts!
I see. I am skeptical, if you can justify something not refering back to your own happiness or some kind of satisfying feeling. Why do you want to worry, if not for benefiting you in an extended way (worrying helps you to feel something for others, so that they can feel for you, so that you can feel happy)? But these are just some questions to think about. Do not feel obligated to change anything!
In my life happiness stands above all, because well-being and happiness seem to be the same. How do you distinguish between them? Or: Why are maximum energy and maximum meaning not leading to maximum happiness?
One possible way to make learning a reality could be in building a product with other people: https://www.lesswrong.com/posts/i2dNdHrGMT6QgqBFy/what-product-are-you-building
If you build something you would use, then your learning is evaluated by yourself through your goals constantly.
This could also be a labeling issue because you cannot identify the function of your habits. For example, limiting yourself in different areas could be a way of keeping your mind from being stressed too much. Trying to overcome this could be beneficial in general, but it could also be detrimental to your health. Of course, you could argue that my point leads to some kind of self-preservational self-deception because every questionable behavior could be considered as “helping in another way”. But I just want to make sure that not every comfort zone has to be labeled as problematic, but merely those which have negative impacts on your primary goals. You should ask yourself: Is “growing” my most important goal? Or is “growing” a means to an end?
I am eager to explore your answer. Why do you think that “stories have the minimum level of internal complexity to explain the complex phenomena we experience”? Is it only because you suppose we internalize phenomena as stories? Do you have any data or studies on that? What’s your understanding of a story? Isn’t a straightforward description not even less complex because you do not need a full-blown plot to depict something like a chair?
Thank you for your work. I really liked the review for your summary of Problem Solving and your general easy-to-read approach. But I also want to have more studies on this kind of education style so I can ground my understanding on independent observations instead of just ideals. I would definitively read a follow-up on the research regarding the books.
Thank you for explaining it. I really like this concept for stories because it focuses on the psychological aspect of stories as understanding something which sometimes is missing in literary perspectives. How would you differentiate between a personal understanding of a definition and a story? Would you?
My main approach to stories is to define them more abstractly as a rhetorical device for representing change. This allows me to differentiatie between a story (changes), a description (states) and an argument (logical connections of assertions). I suppose, in your understanding, all of them would be some kind of story? This differentiation could also be helpful in understanding the process of telling a story versus giving a description.
Unfortunately, you did not explain how your answer relates to “stories have the minimum level of internal complexity to explain the complex phenomena we experience”. In your answer you do not compare stories to other ways of encoding information in the brain. Are there any others, in your opinion?
This is the same conclusion and argument I arrived after reading tivelen’s comment. But my objection would be that a “momentary fluctuation” generally is not a good moral argument. You could doubt every decision because the time you took to not be considered a fluctuation is arbitrary.
I thought about that and also agree with you. But I wanted this room to be thought about as an investigation of personal choice rather than a choice made by others for you. So I opted for the inclusion of this concept. It would be appropriate not to overemphasize this aspect. But it is of course an understandable rejection. Thank you for bringing it to the foreground.
This is a thoughtful analysis of possible effects. Thank you for this. I do not want to have such rooms because I do not want to lose anybody ever. But sometimes there is a tendency in humans for quick decisions which would be supported by such an invention. I suppose this thought experiment shows me that blocking access to easy decision making has potential value.
Pain can also be defined for non-biological beings. For me it is just a word indicating something undesirable hardwired into your being. And maybe there is something undesirable for everything in the universe. One rather metaphysical concept could be a virtue of inertia (described as the resistance of any physical object to any change in its velocity). So you could argue, if you understand the movement of an entity (more concretely its goals), you could find a way to harm it (with another movement) which would result in “pain” for the entity. This concept is still very anthropozentric, so I am not sure, if the change in the movement could lead to or already be understood as a positive outcome for humanity. Or maybe it is not registered at all.
One concept in my moral system relies on the question of how you would respond to permanent retaliation, if you would go rogue. Could you stop an endless attack on your wellbeing because you do things that other people hate? In a world with many extremely intelligent beings this could be very difficult, and even in a world with only you as the bad Super-Einstein it would at least be tiresome (or resource-inefficient), so one super intelligent individual would possibly prefer a situation where they do not need to defend themselves indefinitely. This is kind of similar to the outcome of Wait-But-Why’s concept of the cudgel (browser search for “cudgel”). Ultimately this concept relies heavily on having at least some possibility of giving a Super-Einstein a small but ineradicable pain. So in my opinion, it is not really applicable to a singularity event. But it could be useful for slower developments.
I see, thank you for that and thank you for the conversation.
Thus far I really like the stuff you included and I hope that you will continue to improve the site. You did an amazing job. I think the only criticism I have is the loading speed. I used a performance testing site to look into this and nearly 9 seconds for the frontpage seem to be very high, especially if you compare it to GreaterWrong. I understand the feature focus and I support it, but I just wanted to say that I would really appreciate the effort of a performance optimization in the future. I am aware of the complexity of such a request, and I am sure that you already have thought about this, but I wanted to give you some feedback anyway. Don’t feel obligated to do anything.