The Apprentice Thread 2
A while back, @Zvi set up a Schelling point for mentorship. I, personally, had some pretty good experiences from that thread, and wanted to continue the tradition, now that the old thread’s been inactive for some time.
To see some of my thoughts on mentorship, check out this dialogue between Elizabeth and I.
I’ll be copying Zvi’s formatting for comments:
Replies to this post should take the form of any of the following:
[MENTOR]: A non-binding indication of potential interest in mentorship. Mention that you might, at some point, be interested in taking on an apprentice. This commits you to nothing. Make sure to indicate what you’d be teaching them and what project would likely be involved, and open with [MENTOR]. You are free to include contact info, or not include it and monitor replies.
Replies to this comment to indicate potential interest in being the apprentice, marked [APPRENTICE], which should include a method of further contact.
[APPRENTICE]: A non-binding indication of potential interest in being an apprentice. Mention that you might, at some point, be interested in being an apprentice. This commits you to nothing. Make sure to indicate what you’re interested in being an apprentice in and learning, and an indication of what’s motivating you.
Replies to this comment to indicate potential interest in being the mentor, marked with [MENTOR], which should include a method of further contact.
[NORMAL] You’re free to comment as per normal, but start with [NORMAL] in the top-level for clarity.
[APPRENTICE]
Hi I’m Uli and I care about two things: Solving alignment and becoming stronger (not necessarily in that order).
My background: I was unschooled, I’ve never been to school or had a real teacher. I taught myself everything I wanted to know. I didn’t really have friends till 17 when I started getting involved with rationalist-adjacent camps.
I did seri mats 3.0 under Alex Turner, doing some interpretability on mazes. Now I’m working half-time doing interpretability/etc with Alex’s team as well as studying.
In rough order of priority, the kinds of mentorship I’m looking for:
Drill Sergeant: I want to improve my general capabilities, there are many obvious things I’m not doing enough, and my general discipline could be improved a lot too. Akrasia is just a problem to be solved, and one I’ll be embarrassed if I haven’t ~fully solved by 20. There is much more that I could put here. Instead I’ll list a few related thoughts
Meditation is mind-training why isn’t everyone doing it, is the world that inadequate?[1]
Introspection tells me the rationalist community has been bad for my thinking in some ways, Lots of groupthink, overconfident cached thoughts about alignment, etc.
I’m pretty bad at deliberating once and focusing medium-term. Too many things started and not enough finished. Working on fixing.
(The list goes on...)
Skills I’ve neglected: I know relatively little of the sciences, haven’t written much outside of math, and know essentially zero history & other subjects.
Skills I’m better in: I want to get really good at machine learning, programming, and applied math. Think 10x ML Engineer/Researcher.
Alignment Theory. I have this pretty well covered, and think the potential costs from groupthink and priming outweigh additional depth here. I’ve already read too much LessWrong.
[MENTOR]
I am very good at learning when I want to be[2]. If you would like someone to yell at you for using obviously inefficient learning strategies (which you probably are), I can do that.
I can also introduce bored high-schoolers with interesting people their age, and give advice related to the stuff I’m good at.
Too busy for intensive mentorship, but async messaging plus maybe a call every week or so could work.
Semiconsistently meditating an hour a day + walking meditation when traveling. Currently around stage 3-4 in mind illuminated terms (for those not familiar, this is dogshit.)
Which sadly hasn’t been the past year as much as it used to. I’ve been getting distracted by doing research and random small projects over absorbing fountains of knowledge. In the process of fixing this now.
[APPRENTICE] Sent you a private message
[MENTOR]
This is a bit off-center from the normal LW topic of trying to prevent AI Doom, but I’m interested in helping out people who are interested in law or public policy. I don’t post here much (long time near-lurker), but I am a state government lawyer who works in public health and consumer finance. I am interested in:
Helping people decide the age-old question “should I go to law school?”
Helping young law students, lawyers, or policy-curious folks figure out how to get started in the field and/or where would be impactful for them to work
Help people understand how workaday state government enforcement operates on the ground
Helping lawyers or nonlawyers with their expository/persuasive writing (a lawyer is primarily a professional reader and writer, but don’t ask me to help with creative/fiction writing lol)
Will provide my real name and links to public facing things I’ve done on request. I don’t have any particular need or use for an “Apprentice” per se, so I see what I’m offering as a mentor/mentee model more than a master/apprentice model.
[MENTOR]
I am best known around here for doing short science write-ups (plurality but not majority medical) and occasional broader epistemic or social stuff. I make my living with the research work, some of which looks like my blog but some of which is things like “help entrepreneurs evaluate start-up ideas”. I’m also the other half of hath’s apprenticeship Dialogue.
I am interested in:
providing mentorship on research or writing blogs like mine, for people who are already doing something in that vein. It doesn’t have to be a lot, but I’ve been through too many cycles of people enthusiastic about doing my job until they realize it takes skill and effort, so I only want to work with people who have tried at least a little. If you’re interested in this, please include a sample of existing work in your first contact. “I want to discuss this blog post [mine or yours]” is a really good first contact.
Experimenting with exobraining/body doubling while I work. I expect this to be an excellent way to learn what I actually do, and depending on the balance of labor am willing to pay in money as well.
[APPRENTICE] Contacted via direct message.
No rush but in case you have sent and there’s a bug: I haven’t received anything yet.
Yup, LW drops my messages. Also sent you an email.
Hey, I’ve been getting into writing posts and blogging, and I’ve done some scientific research. Would you be interested in mentoring me?
I’d need more information to answer that (well, the related version of that question I think makes more sense). Could you send me some information on yourself, some favorite work samples, what in particular you’re hoping for? And this overlaps with the last bit, but knowing why you’re asking me in particular is also helpful.
[MENTOR] Join My Brain in thinking about AGI AGI notkilleveryoneism
I am working on AGI notkilleveryoneism. I am good at generating lots of ideas. And I am good at going out of distribution with these ideas. That means I generate a lot of garbage ideas, but sometimes pretty good ones. To see some of them, see the “AGI notkilleveryoneism Interests” section in my bio.
I am interested in having somebody join my brain in thinking. That mainly involves being together, and then understanding a problem better, generating solutions, validating solutions, and implementing solutions. A major component would be keeping our brains in sync through effectively loading each other’s models and ideas. In the ideal case, we are together in the same room, and the room contains a giant whiteboard.
I have done something related when I was studying game design, and empirically it made me much more productive. Since SERI MATS 3, John works together with David Lorell and he says it increases his productivity by 3-4x, which I totally buy. One possible structure that might try out:
UDVI X stands for the iterative process of: (U: first understand the problem domain of X (i.e. Hold Off On Proposing Solutions), D: design a solution, I: implement the solution)
UDVI how to work well together
UDVI finding good research directions in AGI notkilleveryoneism
UDVI Generating ideas
UDVI Evaluate ideas
UDVI Implementing ideas
UDVI how to decide and (for how long to) commit to a particular directions
I would probably do something different if I thought about it longer than 5 minutes, but I hope it communicates the rough idea.
Note that e.g. UDVI of “generating ideas” is already going meta. I imagine this process to be focused as much on the object level as possible, and only jump to the meta-level when you get stuck at the object level (understanding a problem domain better counts as object level in my book). So I am imagining something where you start by thinking about “UDVI how to work well together” but only spend some small fixed amount of time per week on that. Unless there is some problem that comes up. Mostly I am imagining working on the object level and applying UDVI to any problems that come up. Though initially, I think it makes to especially focus on meta.
I have more detailed ideas about specific steps and general strategies than those outlined above. There is some basic stuff that I expect to be good, such as: learning to say ops, I am wrong, I am confused, I don’t understand, and other things in this category. Also having social norms facilitating that seems beneficial.
Some things I am thinking of now might break though. Either because I generated them before I knew about Hold Off On Proposing Solutions, or because I imported them from game design, which is a very different domain.
I also think there is tons of good stuff in John’s MATS Models post. Talking as somebody who experienced all that in person during SERI MATS 2 and the SERI MATS 3 training phase.
I don’t expect that all the time would be spent working together. I expect sometimes it makes sense to split up a task, or make you figure out something for yourself.
Also, there are probably some good <skill-up/exercise> things that I might direct you towards. E.g. Nate’s Giant textfile exercise
I am missing many technical concepts, which I think is my biggest constraint right now. There is a good chance that you have many useful concepts, especially in math, that I don’t. See my LessWrong Bio for a list of my <skills/technical concepts>.
Also, see my LessWrong Bio for more general information about me.
[APPRENTICE]
I’m looking for someone to mentor me specifically w.r.t. «Boundaries» (or, similarly: Cartesian Frames). I’m interested in this both for AI safety (I have a draft compilation post on this that I will be posting in the next few days, or else I’d share it here), and also as a rationality technique. I’m interested in doing research on and/or distillation for this.
[MENTOR]
I am a 25-year-old computer science PhD student and I currently work on natural language processing with neurosymbolic approaches (using a mix of logic and neural networks to do reasoning on a normal text input). I have a (very) high degree of education in math and theoretical computer science. I also have some very limited skills and knowledge for more practical aspects of computer science. Also, I have quite a lot of reflection on the topic of the nature of thought, valid inference, and rational behavior. These are condensed in a currently unpublished book length report. The result of a year-long break I took for personal reflection. I expect to be able to help quite a lot with fundamental reflection that relates to epistemology or rationality.
If you intend to learn about some aspect of mathematics or theoretical computer science I can probably point you toward resources or help you understand technical aspects. I am also willing to serve as a background help for someone going through a math education. Alternatively, I might be willing to help an in depth reflection to which you think I can be relevant.
I can offer some asynchronous email/messages exchange and semiregular conversation, perhaps averaging one or two per month. Ideally, we would schedule conversations quickly when you need them. If you have a very different mode of interaction in mind I am willing to adapt.
[APPRENTICE]
Presentation copy/pasted from the mentor section.
I am a 25-year-old computer science PhD student and I currently work on natural language processing with neurosymbolic approaches (using a mix of logic and neural networks to do reasoning on a normal text input). I have a (very) high degree of education in math and theoretical computer science. I also have some very limited skills and knowledge for more practical aspects of computer science. Also, I have quite a lot of reflection on the topic of the nature of thought, valid inference, and rational behavior. These are condensed in a currently unpublished book length report. The result of a year-long break I took for personal reflection.
I am looking for one of the followings:
Resources and help on the topic of the nature of thought and characterization of valid inference. This is a long standing topic for me. A string of reflections and readings that has been and continues to be an important side project.
Like 1 but with a focus on AI or in general automation of thought.
Help better managing my work and motivation. I need to reduce my work related stress. The help of someone who does a high amount of intellectual work without stress could be precious.
By default, I would imagine a few discussions near the beginning and then much less frequent conversations as needed (once a month?). But that’s just off the top of my head.
[NORMAL]
Whether as a mentor, as an apprentice, or because you think we could work together in some other capacity, feel free to DM me through lesswrong. Give me a few days to get back to you. If I do not answer it probably means your message did not go through. In that case just comment below.
[APPRENTICE]:
For a bunch of these, the minimum viable product for mentoring me is a combination of pointing me to books/textbooks and checking in on me to make sure I actually do it.
Some things I’d like mentorship on:
People willing to review my writing, and accountability on spewing out a bunch of blog posts. (and maybe on starting an actual novel!)
Operations. I’ve run a couple large projects in the past, including a group house, and there’s a lot I can do better. Would love to hear from people who have run group houses or organizations in the past.
Economics: I have most of the 101-level stuff, but could use some more specific knowledge on labor econ. Especially curious about (banking) regulation.
Math: Besides teaching myself calculus and linear algebra, I haven’t really gotten into much complicated math; someone able to point me at more advanced stuff, ideally alignment-relevant, would be much appreciated.
Programming. Ideally, I’d go through a bunch of projects you suggest in Python, with you available for occasional debugging/querying, with the goal of eventually being able to do more technical alignment work.
What are your current skills in Python and programming in general?
(Just approximately, like “never programmed at all”, “never wrote a program longer than one screen”, “senior developer in C++ but never used Python” etc.)
Took APCS (Java 101-102) in high school (culminating with coding Tetris in Java), read through Diveintopython3.net, done a bunch of miscellaneous programs in Python, lots of experience in Linux.
Hm. My background is computer science at university, about 20 years of Java, plus some Python in my free time. Chances are, you know more about Python than I do, so the useful advice I could provide would be in the “programming in general” area, which of course also applies to Python code. Either something theoretical (e.g. finite-state machines), or something from practice (e.g. test-driven development); actually those are the only two examples that come to my mind right now, but maybe if I think longer about it, I will find something more. Also, you could show me your code for a review.
If you want a project, I think a fun exercise could be to design your own toy language and write its interpreter in Python.
If you are interested, send me a private message and let’s figure out how to communicate.
*
Thinking about math, the part relevant for alignment seems to be logic. Could give you a short introduction, but nothing too advanced.
Seems like in both programming and math, I can help you make a step or two forward, but it will still be far from where you want to get. Just saying it in advance, to keep your expectations appropriately low.
Do you have a plot for your novel, or just an idea?
I have an idea on HP:MoR-like novel with different negative forces implying different setting (though still magical world and Hogwarts). I’ve also written a plot for it (with help of ChatGPT), however the plot doesn’t actually matter much to me—I just want to read an exciting story! (It also seems the most realistic way to write a novel, because the finish is not fixed in real life.)
[APPRENTICE]
Not a narrow or specific kind of apprenticeship (training or a project), rather very broad and focusing on learning and academics in STEM areas (advice dispenser, and in cases tutor/trainer).
Fields of Study:
Computer Science: I am planning to major in this at college. So it is kind of important. I am interested in ML, AI, algorithms, Low Level or precise programming, Website Development, and Application Programming. All at a surface level, I am not sure what I want to do after college but I think it would to have an idea of how all of these work in case I find my self especially interested in one or another. I will be taking an introductory programming and problem solving class in the fall.
Psychology: Specifically rationality and learning which according to a textbook I picked up fit in this category. I have a great drive to improve and optimize my ability to learn. Similarly I want to be able to reason accurately consciously and clearly, out loud, in writing, and in my head. Also Philosophy of Logic, I am taking that as a class in the fall.
Math: I love math and plan to learn and practice it no matter what for the rest of my life. It doesn’t matter what math I like to experience the release of endorphins that coincide with the grasping of a new concept and the solving of a difficult problem. The best part is the practice of the process of reasoning. I struggle with math but hope to improve a lot over the summer and have been revisiting algebra, and geometry as I am not taking a math class currently. I will be taking a calculus class in the fall.
Physics: I haven’t taken any physics classes yet so don’t have any rigorous understanding of it but I like the idea of having math that you can use to predict what will happen in the real world. I will be taking a physics course next fall.
Interests: (Less important and only really a bonus)
All the stuff above
Chess: I am learning chess and having a lot of fun I am currently 580 elo and spend a lot of time playing.
Drawing: I am currently taking my first art class (required to graduate) and find my self really enjoying it.
Climbing: I like going bouldering, the problem solving aspect of it is fun, usually it technique over strength and really enjoyable to learn.
Teaching: I really like sharing what I learn, things I made and how I made them.
I am a high school senior I don’t know a lot about anything and currently my only desire in life is to learn stuff. The kind of mentorship I am thinking of is more loose than others described here, I would like to have a contact who has been through college and has experience and or interest in similar things. I would describe it more as a counselor. Someone I could go to for guidance about whatever I am interested in learning, someone who could give me advice on general academics. If I am really struggling to grasp a specific concept or idea, they could help walk me through it. If I don’t know what to do next they could help describe, what is applicable and really worth focusing on. Traditionally an apprentice would work for their mentor, however this is more of a charity project :). Although I would be happy to help if there is anything an extra hand/head would be useful for.
Motivation/Goal: To gain a broad base of knowledge in order to be effective at what ever I decide to do.
For contacting just direct message me.
By the way, if you have a specific question, you can also:
use google
ask on StackExchange
ask on LW as a “shortform” (click your name on the top of the screen, New Shortform)