There are lots of skills I'd pay for but it's generally hard for me to work with people who are unfamiliar with FI philosophy. For example, I'd like video editing to cut down streams to summaries. The main idea is to delete 80% of each stream so that just highlights are left. (Here's an example of a video made by cutting out 88% of a stream. They're pretty common with popular gamer streamers like smallant and zfg who I believe hire video editors to make them.) But I don't think it'd work to get a video editor who knows how to use editing tools but doesn't know anything about FI. He wouldn't know which parts are the highlights! Plus he wouldn't watch my videos normally. It works best to hire an editor who already watches your videos anyway, so then basically you don't have to pay him extra to watch your videos in the first place. It's more efficient and cheaper to use someone who was going to watch the video on his own than someone who wasn't. And it's better if the person doing it actually likes the videos, is interested, is in a position to make judgment calls and additional edits besides cuts (because he has ideas about what would make something better), etc.

Other things I could use: art, design, marketing, other types of video editing, animation, and Keynote polishing (there are lots more tutorials on that channel, but that one video will give you a good idea of what I'm talking about).

I've been having Justin do some work on making ebooks from email archives and adding tables of contents to videos. Those are other good examples of the kinds of skills I'm interested in delegating.

Editing text would be valuable too but basically that takes a ton of skill and I can't trust anyone to edit my writing. The other ones I listed are all easier to do well enough it'd have value to me. I'm less skilled and picky about them.

I'd also be interested in someone to do my newsletters for me. That takes some writing skill and FI knowledge, but a lot less than writing or editing my essays.

I'm sure there are other similar things that I'd also like to delegate. Maybe you could suggest some.

Are any of my fans good at some of these things and interested in doing work for me? Get in touch. I particularly value people who work fairly independently, and come up with some ideas of their own, instead of just following detailed directions. Micromanaging is too much work for me.

Some of these skills, like basic video editing (how to cut parts out), are quick and easy to learn. Others are harder but have lots of resources to help you learn, e.g. there are books and videos about design and marketing (The Futur is an example of a pretty good educational YouTube channel for design and marekting). If you're interested but not already good at any of these skills, you could learn some. Most of the skills require being decent at using computers. Using other software tools can often help you get stuff done faster and easier, e.g. using otter.ai to transcribe videos with timestamps can help you find the good parts to include in a condensed version (then you can edit the video backwards, cutting stuff out from the end first and working towards the start, so when you delete stuff it doesn't change the timing of any earlier parts).

Work would be freelance project work, not full time employment. And not a ton of hours. You could do it in addition to other stuff in your life, rather than choosing one or the other.

I podcasted about whether to start using facecam for some videos. I’m looking for feedback on this decision.

Facecam would give people additional info about what I’m like and how I live, including about mood, emotions and reactions (or lack of). It’d also give info about fashion, blemishes, race, age and some other stuff. People have to deal with IRL so role modeling how to do that, including dealing with hecklers, has some value. Facecam is dangerous for second-handers, but I’m not personally scared about being judged and becoming self-conscious or defensive. I do have concerns about reducing focus on ideas and ceasing to boycott some social dynamics, but people can actually be more distracted by making stuff up than by seeing reality, and showing how I handle social dynamics is a different way to combat the bad ones.

Those are just a few quick thoughts. Hear more considerations in the podcast and share your opinion below.

IGCs are a way of introducing Yes or No Philosophy and Critical Fallibilism. I'm posting this seeking feedback. Does this make sense to you so far? Any objections? Questions? Doubts? Ideas that are confusing?

---

Ideas cannot be judged in isolation. We must know an idea’s goal or purpose. What problem is it trying to solve? What is it for? And what is the context?

So we should judge IGCs: {idea, goal, context} triples.

The same idea, “run fast”, can succeed in one context (a foot race) and fail in another context (a pie eating contest). And it can succeed at one goal (win the race) but fail at another goal (lose the race to avoid attention).

Think in terms of evaluating IGCs not ideas. A core question in thinking is: Does this idea succeed at this goal in this context? If you change any one of those parts (idea, goal or context) then it’s a different question and you may get a different result.

There are patterns in IGC evaluations. Some ideas succeed at many similar goals in a wide variety of contexts. Good ideas usually succeed at broad categories of goals and are robust enough to work in a fairly big category of contexts. However, a narrow, fragile idea can be valuable sometimes. (Narrow means that the idea applies to a small range of goals, and fragile means that many small adjustments to the context would cause the idea to fail.)

There are infinitely many logically possible goals and contexts. Every idea is in infinitely many IGCs that don’t work. Every idea, no matter how good, can be misused – trying to use it for a goal it can’t accomplish or in a context where it will fail.

Whether there are some universal ideas (like arithmetic) that can work in all contexts is an open question. Regardless, all ideas fail at many goals. And there are many more ways to be wrong than right. Out of all possible IGCs, most won’t work. Totally random or arbitrary IGCs are very unlikely to work (approximately a zero percent chance of working).

Truth is IGC success – the idea works at its purpose. Falsehood or error is an IGC that won’t work. Knowledge means learning about which IGCs work, and why, and the patterns of IGC success and failure.

So far, this is not really controversial. IGCs are not a standard way of explaining these issues, but they’re reasonably compatible with many common views. Many people would be able to present their beliefs using IGC terminology without changing their beliefs. I’ve talked about IGCs because they’re more precise than most alternatives and make it easier to understand my main point.

People believe that we can evaluate both whether an idea succeeds at a goal (in a context) and how well it does. There’s binary success or failure and also degree of success. Therefore, it’s believed, we should reject ideas that will fail and then, among the many that can succeed, choose an idea that will bring a high degree of success and/or a high probability of success.

I claim that this is approach is fundamentally wrong. We can and should use only decisive, binary judgments of success or failure.

The main cause of degree evaluations of ideas is vagueness, especially vague goals.

---

I'll stop there for now. Please post feedback on what it says so far (rather than on e.g. me not yet explaining vague goals).

This is internetrules's discussion topic. He has agreed to only post as "internetrules" in this thread.

Here's the YouTube playlist where I tutor internetrules.

A discussion needs to make sense simultaneously from both people’s points of view (povs). That means each person gets all his requirements met. (More than two people is harder and I won’t address that specifically.)

If my requirements for the discussion aren’t met, then we don’t have mutual benefit from the discussion. If yours aren’t meant, then we don’t have mutual benefit. The discussion should only happen if there is mutual benefit.

This means you can use my discussion methodology, or propose an alternative that I find acceptable, or you shouldn’t expect a conversation with me.

If someone refuses debate and also wants to be some sort of public intellectual – rather than leaving ideas and truth seeking to others – then he ought to say why. I do say why. I’ve written about my discussion methodology and I’m responsive to critical discussion about it.

Sharing one’s reasoning means that mistakes on either side can be potentially fixed. It leaves a path open for progress to happen, regardless of who is mistaken. And I try to be extra tolerant of methodology and framework differences when people try to discuss my methodologies and frameworks themselves. Demanding someone fully use my approach to discussion before discussing/criticizing my approach to discussion would be problematic. But I do expect people, even in those conversations, to try to use an approach that makes sense and is productive from my point of view. If they can’t or won’t tell me how it should make sense or offer value from my perspective, and I don’t see it (after trying some), then it’s not going to work. If I can’t see how their comments will lead to progress, and they won’t tell me in a way that addresses my concerns, questions, criticisms, etc., then it’s not going to lead to progress for me.

There are aspects of discussion that I’m flexible about. Some things I prefer one way but I can deal with them being another way. They aren’t dealbreakers. I see how progress can be made even if something is a bit inconvenient or non-optimal.

There are other aspects of discussion which I’m inflexible about. I don’t want to meet people half way or compromise. E.g., I don’t think it’s productive to criticize things I don’t think I said and refuse to use quotes. I don’t see value in having a discussion of that nature. Similarly, I don’t see value in people saying things I consider unclear or ambiguous, and then not being very responsive to clarification requests. People often say unclear things faster than then clarify any. If you won’t or can’t tone down the unclear, “sophisticated” or “advanced” statements to the point where communication is working, then I don’t know how to have a productive conversation with you.

I can be flexible about the occasional statement I have a problem with, and drop or ignore it without clarification. But if it’s a frequently recurring problem affecting the main points of the conversation, then either initial communication or clarification needs to be working reasonably well.

I also want reasonably organized discussions. There is lots of flexibility here but it can’t just be mass chaos. People who won’t cooperate with attempting to organize things make bad discussion partners.

I require that people respond to me. If people won’t answer my questions, then I don’t know how to have a mutually beneficial discussion. I am responsive to direct questions. Often people don’t use or respond well to direct questions or requests, and this makes discussion hard. They want me to respond to things they don’t say, and I want them to respond to things I do say, and neither of us is getting what we want. I won’t switch styles without my concerns being addressed, but the people who want to operate by unwritten rules and social hints don’t want to discuss that system itself and acknowledge what they’re doing, so my concerns don’t get addressed. Often instead they agree to use my system of saying things in words but then don’t. They haven’t practiced it and don’t really know how to do it, and don’t acknowledge their beginner status and work on learning, so then discussion fails. I don’t know what to do about that besides either not discuss or they try to learn and work their way up at rational, explicit discussion. I’m open to alternatives if someone can offer one that offers mutual benefit and makes sense from my pov.

I don’t know how to have a conversation that benefits me when people are doing a bunch of unacknowledged social dynamics, passive aggressively sniping at stuff, being dishonest, and refusing to (or more often incapable of) analyze text literally. And people get offended if I express problems like this. They also get offended if I question their competence. But what am I to do? Refuse to discuss and refuse to say why? Dishonestly take the blame for the discussion’s failure? Present myself as unwilling to discuss? No. I would discuss but have certain concerns. If people don’t want me to name concerns like those, they shouldn’t converse with me in the first place. I’m not going and doing this to random people who never signed up for it. I run forums aimed at rational, critical discussion. If people don’t want criticism they should go elsewhere. People come to me and I’ve written a ton to try to warn them about what to expect. And I’ve been open to suggestions on how to better warn people but no one seems to know any fixes. It’s hard to fix by writing different warnings since in general people don’t read much before discussing, and even if they do they usually don’t understand much of it. I occasionally do go to other forums but I pick ones that claim to be focused on rational discussion and I’m less assertive or pushy there and I much more often will drop conversations without explanation. I think it’s OK for me to stop responding there because anyone who cares can come to my forums and debate me, or can make an explicit request that I explain why I left. (I do make some effort to let people know those options exist.)

One of the things I commonly want in discussion is persistence. I’ve already had a lot of discussions. I don’t want to go over old ground at the start of the discussion … and then stop there. I understand that may be new ground for others, but if that’s going to be the whole discussion then I often don’t want it. I’m more interested in unbounded discussions that try to reach conclusions about important issues. Lots of people think their opinions and ideas don’t really matter. That is their privilege but it isn’t what I’m looking for.

A common discussion problem is people make statements that rely on premises that I don’t share. Either I disagree with some of their premises or I’m unfamiliar with some, or both. This is a reasonable and expected thing to happen some. But people should understand the issue and be willing to discuss the premises instead of continuing on the original topic. And they should start building up a mental model of me and should get better at saying things that don’t read to me as skipping steps (using premises I don’t know) or building on stuff I disagree with instead of speaking to the disagreement.

People are bad at lots of this stuff. Most people are pretty incompetent at discussion. But most of them won’t admit it. I won’t simultaneously treat you like a beginner, give you leeway and help you learn to discuss better while also treating you as a peer who is seriously challenging my ideas. People often want both – they e.g. want me to go easy on them while pretending I’m not going easy on them, so that they look good. And they want me to do that without being asked. It’s dishonest and doesn’t benefit me. And their sometimes implied offer to do the same for me in return is not appreciated. You can’t have it both ways and the excuse “I have great ideas; I’m not just great at debating” is not going to fix it. If you want help figuring out how to have a productive discussion, say that. If you think you’re in a position to correct me on stuff, say that. But don’t try to have it both ways at once. If you really think you can do both at once, say so, and try to explain why and how.

It’s hard for me to help people who refuse to present themselves as learners. When I try to help them learn, they often find it condescending and threatening to their implicitly claimed status as experts. A lot of people should be trying to learn but instead try to debate, and are really bad at learning from/during debate, and so it doesn’t work, and the discussion can easily shift to the issue of them doing a bunch of stuff they’re incompetent at, and so they ought to figure out a course of study to become competent first, and people often hate that and find it threatening to their self-esteem and social status. But there’s no benefit from my pov to ignoring recurring patterns of incompetence that are preventing the original topic from making progress. And I don’t want to quit the discussion without saying why. Again, all I want is a way to continue that offers value from my perspective. And you should have a way of continuing that offers value from your perspective. And that may not happen, in which case we need not talk. Lots of people just don’t want to be judged, and don’t want anyone to talk openly about problems discussing with them. If that’s you, don’t start a conversation with me, because I do judge and I do talk about my judgments and reasons.

If you present yourself as a beginner/student/learner who’s trying to improve and isn’t very good at stuff yet, you won’t find me very judgey. That’s fine and I’m sympathetic to that.

If you present yourself as an expert who knows I’m wrong about important issues, then that’s not something I want to ignore; it’s something I want to reach a judgment about. Can and should my judgment be impersonal? The short summary is that people mostly consist of ideas, so impersonal criticism of ideas is often threatening and scary to people, and feels personal. And also there are often patterns of error in ideas someone shares – e.g. they try to argue that I’m wrong about several things and make recurring mistakes – and speaking about those patterns and their causes is personal. Saying those ideas (that Joe said) contain patterns of error caused by specific thinking methods (the ones that Joe uses) is not going to to make Joe happy. That kind of wording change doesn’t address the real issue, which is that part of Joe’s identity is connected to the ideas being criticized.

If you want to be treated like a beginner every time you’re wrong, but also to spend most of your time trying to argue that I’m wrong instead of trying to learn anything, it’s not going to work. Learning via debate as a primary mechanism is hard and most people have no idea how to do it. It’s not taught effectively anywhere. People don’t go to classrooms, debate their teachers, and learn a bunch by doing it. That is not a common or standard way to learn. If you’re trying to learn in a way that’s dramatically different than all the learning that happens from interacting with parents, teachers or books, you should have some sort of plan and explanation of what you’re doing, how you developed the skill, why it’ll work, etc. If you don’t have that, don’t assume you know how to multitask debating and learning. Try doing one thing at a time, and only maybe do two at once if you’ve gotten both of those things to work well multiple times individually.

People often want to talk about sophisticated, advanced stuff with me, but they don’t know the medium stuff that builds up to it. That doesn’t work well and they usually don’t want to hear about the gaps in their knowledge. But it doesn’t work well from my pov to try to fill in those gaps as short tangents to an advanced debate. Learning those medium things is hard enough when it receives full focus for weeks.

If you don’t like any of this, or want something else, say so. Ask for what you want and we can discuss my concerns, if I have any. I’m open to other stuff as long as you can tell me the benefit from my pov or I can figure that out myself.

George Reisman tweeted:

[Trevor Dillinger wrote:] You have no right to drunk-driving. Same with COVID-19 spreading.

Your comment would apply to the Chinese Communist Party, who knew they were spreading Covid 19.

No one should be virtually imprisoned in a “lockdown” without benefit even of probable cause to suspect that he might have the disease, let alone without a trial or even the existence of a law that he is alleged to have broken.

The proper response would be to avoid contact with people especially susceptible to the disease and for them to avoid contact with whoever might give it to them. That’s it. For the rest, the purpose of life is not to avoid giving Covid 19 to others or getting it from them.

I disagree with Reisman despite agreeing with lots of his principles and views. This post is me thinking out loud about coronavirus lockdowns vs. individual freedom to stay home or risk going out.

Guessing a Reisman view: If you live with someone and they go out, too bad. Don’t live with people you can’t coordinate risk taking with.

Guessing a Reisman view: If your commute and job aren’t safe enough, quit. If you didn’t save money, oops, too bad. Or maybe you can get your work to make changes (plastic screens, masks, sanitizer, fewer customers inside at once, etc.) and get a car instead of public transit.

This stuff, like I think Reisman wants, is awkward in a world where the government requires people to do various tasks in person. Like go to the DMV IRL. If the government keeps requiring that, while also being hands off about the pandemic, they’re risking people’s lives. Solution: instead of lockdowns the government cancels a lot of their red tape so fewer people need anything, and moves the rest online.

It’s awkward in a world where too many employers do the minimum required by the government. They’re used to being bossed around instead of taking initiative to make good policies. So if the government stops bossing people around we get chaos.

It’s awkward in a world where people pay taxes for public education and expect their kids to go to govt schools and then there’s a pandemic and if they want to be safe they may have to give up major resources they planned around having.

It’s awkward to tell people to quit their jobs to avoid pandemic risk in a world where you’re punished for quitting in some ways. Like you lose unemployment and severance benefits which you’d get if you were laid off (fired without doing anything wrong). But if you’re quitting cuz pandemic, that is an external problem outside your control, and you might actually deserve unemployment benefits.

We live in a world where hospitals can’t say “guys if you don’t wear masks we’re cancelling your health insurance and firing your as customers” or similar. The government has tons of laws requiring them to give care regardless instead of demanding their customers take appropriate steps to not get infected. They can’t just refuse ventilators to people who acted irresponsibly. In a better world, they could, so there’d be way more lockdown type pressures from non-government sources. Similarly, health insurance can’t offer discounts for low covid risk behaviors or raise prices for risk takers.

What if I want to stop going to the gym because of the lockdown, but I had signed up for a year long membership plan (as is typical at US gyms). I claim the gym is no longer providing the service I signed up for: safe workouts. The gym says: what!? we are still open like normal! The government is going to have to play a role in deciding stuff. Am I being overly risk averse and I’m still on the hook for gym dues, or am I being reasonable and the gym operating like normal is a bad idea? The government needs some kinda general policy about this, not “no comment”. That way, such things can be resolved by the courts in a consistent predictable way (not the chaotic choices of each individual judge or jury). And we want almost none of it to go to court in the first place, which would be very expensive and overload the system – but if the results are clear and predictable enough due to consistent, standard policies then people can follow that without needing their own individual court case.

You can’t disentangle the government from life overnight just because you like freedom and government pandemic policy is inconvenient and, in various ways, stupid.

Government does a ton to prevent new businesses and products. They regulate where you can create buildings, what buildings you can create, whether you’re allowed to run a business of a particular type, whether a product or service may be sold, the price at which it may be sold (e.g. anti-gouging laws), the many safety checks you must submit to, the vetoes you must give your neighbors in many cases, and much more. The government has stopped a large amount of hand sanitizer and mask production. One of the bottlenecks has been the stuff you add to alcohol to make it undrinkable (undrinkable alcohol is the main ingredient in hand sanitizer), which is needed because the government wants to have a bunch of extra rules and taxes related to drinkable alcohol. The FDA, CDC and others restrict new medicines, drugs, vaccines, virus tests, volunteering for treatments, experiments, uses of lab animals, uses of volunteer human patients, and so on. In that world, where free market response to covid is so limited by govt, it doesn’t make a ton of sense to also ask the govt to be hands off regarding covid. You could try to ask the govt to manage the medical response to covid but be hands off on freedom of travel and other activities by citizens, but i think that doesn’t make sense when those activities are medically relevant.

We live in the world where the govt doesn’t just watch as other actors handle everything. We don’t have other non-govt actors set up to properly evaluate a pandemic, communicate to the whole country about what to do, etc. The govt is bad at it too but they do have agencies and budgets that are meant to address this stuff. And it’s also a world where if the govt says “X is a bad idea” but leaves X legal, people assume the warnings are unserious. And that’s a generally reasonable assumption: the govt actually does ban all kinds of things they really think are bad, and gives all kinds of way way overly cautious warnings that are not backed up with actual rules. Plenty of way overly cautious stuff is backed by rules, so having no rules really signals no real danger. So leaving bars and restaurants and gyms free to operate as normal would communicate to the public that there’s no real danger.

This is similar to parents (govt) who punish their kids (citizens) over major and minor things, and sometimes over nothing or the parent’s error, and they have rules for all that stuff – if that is your general policy, then telling your kid “I think eating cyanide is a bad idea” while not making any rule or threatening any punishment would be irresponsible and communicate that eating it isn’t much of a big deal (because everything else that’s a big deal, and a lot more besides, gets rules and threats).

There are lots of things wrong with the govt but trying to change some specific policies in response to a pandemic is bad timing and planning. Public health policy to defend against ~3 million Americans dying of a disease is the wrong govt changes to start with and we should generally do more changing/reforming during calmer more normal times when it’s easier and there are fewer unusual factors making it hard to tell how successful the changes are.

The government coordinating mass action to protect millions from death is one of the last types of government functions we should be looking to get rid of, not one of the first.

It’s fine to give advice about govt pandemic policy and suggest e.g. that beaches should be left open since a lot of the spread happens indoors. The govt can be questioned and argued with and that’s no problem. That’s part of the existing system. It’s a different matter to suggest drastic changes to the powers and style of government and say any government control over the pandemic is illegitimate. Debating the right plan is fine; saying “I don’t really want to have a government except a few special cases, therefore we should get rid of our pandemic response” is unreasonable (terrible transition plan and not trying to engage with actual live political issues) and focusing just on saying that govt pandemic response violates freedom, without even connecting that to a broader abolishing of most govt functions – just special casing pandemic response as something to get rid of – is unreasonable.

The order of reforms matters in general. E.g. we’ll need welfare reforms before having fully open immigration. And we’ll need to stop subsidizing drug use before legalizing all the drugs. Although “legalize drugs; victimless crimes shouldn’t be crimes” sounds nice in various ways, it interacts badly with current policies about tax-funded rehab, needles, medical care for drug users, etc. (Or requiring everyone to buy health plans that cover preexisting conditions and don’t charge extra to drug users – that is a forcible subsidy from regular citizens to drug users.) Although “let anyone come here and work if they can afford a home” sounds nice, it’s a problem with rent control, tons of restrictions on building homes, minimum wage laws and other price controls on labor, tons of rules restricting starting businesses that could hire the new immigrants, as well as all the tax-funded welfare available to people who live here.

If the govt’s pandemic response was like “good luck guys and enjoy the freedom of not being oppressed by your govt” – but everything else about the govt stayed the same – it’d be awful. It’d be kinda like a parent who micromanages most of his kid’s life and then is hands off about one thing.

I’m in favor of tons of govt reform. I want a govt that does way less. But that needs to be done with general principles and broad plans. That ongoing project shouldn’t be especially connected to the pandemic besides using some pandemic response as examples of how badly the govt manages stuff. Minarchists and anarchists shouldn’t just demand total freedom about every individual issue that comes along, out of context, as a local optima. They should look at the bigger picture and figure out some good places to reform and focus on advocating that instead of wanting immediate pro-freedom changes to whatever political issue they’re looking at with no broader plan.

---

i wonder if reisman opposes the govt controlling its borders to protect citizens from coronavirus

should we have total internal freedom but travel ban china? or just let everyone in from anywhere – too bad for our citizens who are concerned about getting sick?

also:

The proper response would be to avoid contact with people especially susceptible to the disease and for them to avoid contact with whoever might give it to them.

so, avoid contact with old ppl but do have contact with their grand kids, and also the old ppl should avoid contact with their own grand kids? or they should ask their grand kids to heavily social distance and stuff?

what about old people who live in a care home and don't want to die? how should they protect themselves? too bad for not having the foresight to choose a home with great pandemic policies? too bad for not remaining independent in their own home? is it ok for the government to ban elder care workers from working at multiple different homes? should the old people, some of whom have significant mental deterioration at this point, negotiate with their care homes to adopt good policies like firing any workers who won't avoid all other care homes? should they have arranged for family members or hired proxies to be prepared to negotiate such things on their behalf? we don't live in that world where such things are reasonably expected of people. we live in a world where the govt is expected to make some policies. today i think "you can't work IRL at multiple retirement homes during the pandemic" is a good rule that more jurisdictions should have, even though i can imagine a different society where a similar result would be achieved in a more freedom-friendly way.

---

and re people just quitting and staying home if they want to avoid risk. which most people aren't in a position to do. but anyway, what happens if all the ppl who do food work quit and stay home?

i rely on other ppl working. i want policies that let “essential” workers keep doing their jobs with a lot of added safety. if people working in food, medicine, infrastructure (like water, power cables, and internet cables) etc. were mass quitting, that'd be awful for everyone. but if they are told "you can quit or not quit; freedom! yay!" then a lot will quit and everyone will be fucked. what keeps more of them working is that other parts of society are actually trying to take action in regards to the pandemic, like wearing masks when entering grocery stores, and trying to social distance so they don't get and spread it. and that's partly people being reasonable and partly govt policy.

if you just have all the unreasonable people going around being risky and all the reasonable people staying home, even if they could somehow afford that, then you'd lose a lot of important workers without replacement. partly cuz they have training and skills and stuff (including reasonableness). partly because replacing lots of workers is hard. partly because there are lots of govt restrictions requiring credentials and safety training and stuff to do jobs or start new businesses to pick up slack when some existing businesses are understaffed.

curi:
FI doesn’t have a lot of guided learning. it requires ppl to be able to guide themselves some. reading stuff is one of the most guided parts. i have lists of stuff ppl can read.
most ppl aren’t very good at guiding themselves instead of being told what to do
like it’s useful to learn a variety of standard things that our society knows. some economics, psychology, history, grammar, science, etc.
a lot of ppl won’t go find resources and work on that on their own
it’s not realistic to get really good at FI without knowing mainstream stuff too like an “educated” person would know
ppl are used to a teacher telling them what to do
InternetRules:
so like with games i dont think there is much guided learning in say OW. but if u were following the SMO speedrunning guide that would be like guided learning how to speedrun
curi:
but they need their own “motor” as Rand calls it. their own ability to run their own lives. a lot of why they dislike criticism is because they feel like it bosses them around or makes them do things. they don’t know how to run their own lives and use criticism to make their life better.
InternetRules:
with OW u can be like "what things should i learn? forwards backwards? mechanics? team comps? counters?"
curi:
OW has decent guidance available. you can vod review your own play, watch strategy videos, watch vod reviews done by top players, etc
there are videos with guidance about things to practice
but it’s less guided than school
there isn’t a textbook telling you stuff step by step
InternetRules:
so like if u have someone vod review your gameplay and they are like "u r really bad at X" then that would be more guided if u try to practice X
curi:
and yeah some speedruns have really good guidance like smallant’s guide vids
that’s better guidance than schools give
InternetRules:
if they say like "u should practice X, Y, and Z in what ever order u want" that would be less guided i htink
if they were like "do X, then Y, then Z" that would be more guided
curi:
guidance can be a problem b/c it’s hard for one set of instructions to work well for everyone. ppl have different goals, preferences, prior knowledge, likes, dislikes, questions, confusions, etc.
often ppl try to fit themselves to the guidance even though it’s not a great fit. but sometimes they won’t do that at all or complain a bunch. their attitude depends on how badly they want to learn it and what alternatives they have and the social status of the guide.
InternetRules:
right now i think im trying to figure out like what guidance and what counts a guidance.
curi:
if they are happy to treat someone as an authority they will defer more and try to adjust themselves to make it work, and blame themselves if it doesn’t. but with people who society doesn’t endorse as a good master/leader/etc then people can be way more hostile.
InternetRules:
Tooey seems very much like that
curi:
guidance is like advice, tips, instructions ... stuff that tells you how or what to do.
InternetRules:
there was a part that said he like caused some of his students or something, some ppl he adviced they killed themselfs cuz they didnt like life or something
so you can also guide your self
curi:
it’s always partial. ppl can’t control you entirely with every detail. even with like slaves being whipped to pick cotton, no one told them how to close their hand around the cotton and which muscles to use. they were expected to make it work somehow and whipped if they screwed it up to motivate them.
InternetRules:
instead of like someone else telling u "ur bad at X" you could watch your own vod and be like "im bad at X" then start working on X. both of those would be guidance i think
curi:
actually a lot of school is like that. teachers are really bad at teaching but they know how to keep punishing kids to pressure the kid to learn it himself somehow.
pioneers don’t have guidance. they go exploring and try to figure things out. like taking a wagon to oregon in the past without a good map or knowing what you’ll do there, and you hopefully arrive and try to figure out how to make a life there. you know some basic stuff in advance like there are trees and rivers. you can farm and hunt. but you figure out details yourself.
when a new video game comes out, some ppl explore it and figure out what works well in the game and whether it’s a good game. most ppl play badly at first and then watch some guides to tell them what’s good.
InternetRules:

often ppl try to fit themselves to the guidance even though it’s not a great fit. but sometimes they won’t do that at all or complain a bunch. their attitude depends on how badly they want to learn it and what alternatives they have and the social status of the guide.

so you should try to change the guidance in some way if it doesnt fit u i think. maybe its like "ok u should learn strategy then mechanics" but u really like mechanics and doing things like trickshots so u could decide to do that first before strategy parts.

that would be like changing the guidance to suit you better
and you could look at specific parts of the strategy part of the guidance to help you get more trickshots, like u could learn about positioning which helps you stay alive longer and be in better spots so you get more and better trickshots

guidance can be a problem b/c it’s hard for one set of instructions to work well for everyone. ppl have different goals, preferences, prior knowledge, likes, dislikes, questions, confusions, etc.

im trying to think aobut the "ppl have different goals part" and how that effects guidance

preferences, likes, and dislikes make immediate sense to me.

if a guide is telling u how to be good at the game and like win more, but u specifically just want to do trickshots and dont care to much about winning, u just dont want to be like hard throwing with ur trickshots, then i think thats like a different goal than the guide is intending
so i guess like the info section in discord has some guided stuff. like "Everyone should read the FI articles" and saying some stuff that ppl should read and discuss and like to introduce yourself
unguided would be like if u had the FI articles but u didnt tell ppl to read them. and ppl like just by them selfs think "oh FI articles those seem relevant and important i should read those"
ok so theres like benefits to guided stuff and also drawbacks i think
like if ur trying to do something new that no one has really done before but ur super use to using a bunch of guided learning that would be harder
curi:
i’d have more guided stuff but it takes work to make it
InternetRules:

guidance is like advice, tips, instructions ... stuff that tells you how or what to do.

so like telling someone about the "site:" command on search engines would be guidance about how to use search engines

when a new video game comes out, some ppl explore it and figure out what works well in the game and whether it’s a good game. most ppl play badly at first and then watch some guides to tell them what’s good.

so like if u watch pros play and try to copy that, i think the pros gameplay would also be guidance
curi:
sure re “site:”. guiding ppl for how to do small things is common and often works well. there are YT videos on how to repair a leaky sink or change a bike tire or whatever.
InternetRules:

pioneers don’t have guidance. they go exploring and try to figure things out. like taking a wagon to oregon in the past without a good map or knowing what you’ll do there, and you hopefully arrive and try to figure out how to make a life there. you know some basic stuff in advance like there are trees and rivers. you can farm and hunt. but you figure out details yourself.

so like maybe after a year guidance would be given to like ppl trying to get to the west coast, like the pioneers who already made it could give tips like:
after X miles food is really scarce for Y amount of miles, so make sure u have enough food.
and that would be guidance
curi:
how to learn to think well is harder to guide. it’s a big, broad topic and the best actions depend on what you already know, what emotions block what options, your available resources, what your friends think and how much you want to stay similar to them, etc. it gets really complicated. that’s one of the reasons for more self-guidance. you can take into account your situation way better than someone who is writing an essay for everyone and who doesn’t know about your personal situation.
InternetRules:
so like some ppl could write guidance on specific things, like mb your more compatible with objectivism than CR, so you start with objectivism, or the other way around, and then u could like and guided content for those specific topics
so you could guide your self on what to start learning first i guess

how to learn to think well is harder to guide. it’s a big, broad topic and the best actions depend on what you already know, what emotions block what options, your available resources, what your friends think and how much you want to stay similar to them, etc. it gets really complicated. that’s one of the reasons for more self-guidance. you can take into account your situation way better than someone who is writing an essay for everyone and who doesn’t know about your personal situation.

so like having an overview of like how to learn to think well could be good, it like could point you to a bunch of stuff then u can decide which ones to start with. but having a direct guide like: "start with objectivism, then CR, then read szasz, then popper
" would not work out for everyone
wait CR is pretty related to popper i think its like kind of his philosophy
curi:
ya CR = popper
InternetRules:
but like guided learning like that might work for some ppl who are already compatible, but if for some reason u really hate objectivism then it would be better to start with other stuff
curi:
when people change guidance, there’s a risk they screw it up. they often don’t understand why it is the way it is or what kind of changes would work well or not.
InternetRules:
so like maybe u want to do popper before  deutch, but like reading deutch first might help u understand popper better
curi:
an example of changing guidance is it says “practice X” and you don’t want to do that b/c you think it’s boring or you think you’re already good at X and don’t need practice.
InternetRules:
so like if its like "learn addition, then times tables" u might think your already good enough at addition and just skip to times tables
but u dont even know what 5 + 3 is off hand
curi:
books that aren’t “educational” – like textbooks and homeschool work books – are generally pretty unguided. like The Fountainhead doesn’t tell you what steps to take to change your life. science books will tell you some science ideas but they won’t guide you through practicing it, thinking through questions you have, and otherwise learning it. they usually make it pretty easy to read the book and keep thinking “yeah i agree” but then after you’re done you can’t actually do the math or figure out what’ll happen in some experiments because you didn’t really learn it well.
pro gameplay is an example. that helps compared to not having an example. but it isn’t guidance like “do this then do this”. you have to decide what to do from the example.
InternetRules:
so i think like figuring out bosses in vindictus is more self guided
curi:
legendarma makes tutorials but ya lots of ppl just practice until they figure it out
ok with you to blog this chat?
InternetRules:
its fine to blog this chat yes

Andy B has been harassing my FI community using many false identities. He left after I caught and exposed him, but he returned in Aug 2020. He’s written over 100 new curi.us messages under the names Periergo and Anonymous, and his Periergo Less Wrong account has been banned by Less Wrong for targeted harassment against me.

Unfortunately, he succeeded at his goal of destroying my discussions with Less Wrong.

Andy’s actions – including threats, doxxing, spamming, infiltrating the FI Discord with multiple sock puppets for months, and posting hundreds of harassing curi.us messages – violate multiple laws. He’s attacked several other FI members, not just me. His real name is unknown.

If anyone is actually willing to discuss this matter, I will provide additional evidence as appropriate. I have extensive documentation. I already posted evidence, and none of the facts are disputed.

Andy’s Friends

Andy is a David Deutsch (DD) fan who is friends with the “CritRat” DD fan community, including the “Four Strands” subgroup. They have turned a blind eye to Andy’s actions. They’ve refused to ask him to stop or to say that they think harassment is bad. The CritRat community is toxic and has also been an ongoing source of (milder) trouble from people besides Andy.

Andy’s friends include many of DD’s associates and CritRat community leaders. They know what he’s done but apparently don’t care. They’re providing him with encouragement and legitimacy in a social group, and some of them have egged him on. The public communications with Andy that I link below are all from months after Andy’s harassment was exposed.

• Lulie Tanett has friendly tweets with Andy (related, she tweets saying we need to use force and threats, which she considers a useful “technology”). She’s DD’s current closest associate and long time IRL friend, who he often promotes on Twitter and does joint projects like videos with. She’s promoted on DD’s website. She has a history of knowingly associating with people like online harassers, doxxers and spam botters.
• Sarah Fitz-Claridge follows Andy on Twitter. She co-founded Taking Children Seriously with DD and is his long time IRL friend. She has a hateful attitude towards ET.
• Sarah’s husband has friendly communications with Andy on Twitter. He’s had discussions with DD for many years. He’s said hateful things about ET.
• Brett Hall tweets with Andy (examples 2 and 3). He’s promoted on DD’s website and by DD’s tweets, and he’s said hateful things about ET.
• Samuel Kuypers tweets with Andy. He’s promoted on DD’s website and recently co-authored a physics paper with DD.
• Bruce Nielson tweets with Andy (more). He’s a Four Strands leader/moderator.
• Aaron Stupple tweets with Andy. He’s a Four Strands leader/moderator.
• Dennis Hackethal talks with Andy publicly and was co-moderator of a DD related subreddit with Andy. He’s a Four Strands leader/moderator who has libeled and plagiarized ET. DD has promoted him on Twitter.

All of these people, as well as DD, have so far refused to communicate about this problem. They apparently have no interest in a truce or deescalation. They’re making the problem worse.

They’ve stated no grievances against FI, no terms they want, no willingness to negotiate, and no approaches to problem solving that they’d try. They’ve given no explanation of how they view the Andy problem, and they haven’t said anything to discourage the harassment coming from their community. They haven’t made no contact requests either; they just ghost me and others without explanation. (Except Dennis asked me not to email him again about Andy, which I haven’t.) I’m willing to communicate using proxies, involve a neutral mediator, or take other reasonable steps.

The situation is asymmetric. The FI community is peaceful. Harassment doesn’t come from FI towards CritRats or anyone else. If any FI member did harass someone, I’d ask them to stop or ban them, rather than encouraging them. (Or I’d discuss my doubts about the accusation, if I had any. What I wouldn’t do is ignore the matter with no comment, and ghost the victim, while continuing a friendly relationship with the person accused of extensive harassment, illegal actions and aggressive force.)

Warning

Andy hasn’t harassed FI since his Less Wrong account was banned recently. Maybe he’s decided to leave me alone because he got caught again? I hope so. Or maybe he’ll continue on any day.

Despite Andy’s repeated aggression against FI, as well as the misdeeds of other CritRats, I would still prefer to deescalate the situation.

But this is a chronic problem which is doing major harm, and Andy has a pattern of returning to harass again. I’ve been extraordinarily patient and forgiving, but this can’t go on forever. Andy started harassing us two years ago. If any CritRats are willing to speak to me about deescalating or improving this situation, please contact me (comment below, email [email protected] or use Discord). So far the communications of myself and others just get ignored by CritRats. They’ve repeatedly ghosted the victims instead of the harassers.

So I’m issuing a warning: If Andy comes back to harass me again, I will hold his supporters accountable. If you’re encouraging Andy while not even giving lip service to peace, and you’re refusing to communicate about any conflict resolution, then I will blame you and take defensive actions like writing about how you’re violating my rights and sharing evidence. I’ll particularly criticize the community leaders, especially the top leader, DD. If (like me) you don’t want this outcome, clean up your community and stop harassing FI.

habryka wrote about why LW banned me. This is habryka’s full text plus my comments:

Today we have banned two users, curi and Periergo from LessWrong for two years each. The reasoning for both is bit entangled but are overall almost completely separate, so let me go individually:

The ban isn’t for two years. It’s from Sept 16 2020 through Dec 31 2022.

They didn’t bother to notify me. I found out in the following way:

First, I saw I was logged out. Then I tried to log back in and it said my password was wrong. Then I tried to reset my password. When submitting a new password, it then gave an error message saying I was banned and until what date. Then I messaged them on intercom and 6 hours later they gave me a link to the public announcement about my ban.

That’s a poor user experience.

Periergo is an account that is pretty easily traceable to a person that Curi has been in conflict with for a long time, and who seems to have signed up with the primary purpose of attacking curi. I don't think there is anything fundamentally wrong about signing up to LessWrong to warn other users of the potentially bad behavior of an existing user on some other part of the internet, but I do think it should be done transparently.

It also appears to be the case that he has done a bunch of things that go beyond merely warning others (like mailbombing curi, i.e. signing him up for tons of email spam that he didn't sign up for, and lots of sockpupetting on forums that curi frequents), and that seem better classified as harassment, and overall it seemed to me that this isn't the right place for Periergo.

Periergo is a sock puppet of Andy B. Andy harassed FI long term with many false identities, but left for months when I caught him, connected the identities, and blogged it. But he came back in August 2020 and has written over 100 comments since returning, and he made a fresh account on Less Wrong for the purpose of harassing me and disrupting my discussions there. He essentially got away with it. He stirred up trouble and now I’m banned. What does he care that his fresh sock puppet, with a name he’ll likely never use again anywhere, is banned? And he’ll be unbanned at the same time as me in case he wants to further torment me using the same account.

Curi has been a user on LessWrong for a long time, and has made many posts and comments. He also has the dubious honor of being by far the most downvoted account in all of LessWrong history at -675 karma.

I started at around -775 karma when I returned to Less Wrong recently and went up. I originally debated Popper, induction and cognitive biases at LW around 9 years ago and got lots of downvotes. I returned around 3 years ago when an LW moderator invited me back because he liked my Paths Forward article. That didn’t work out and I left again. I returned recently for my own reasons, instead of because someone incorrectly suggested that I was wanted, and it was going better. I knew some things to expect, and some things that wouldn’t work, and I'd just read LW's favorite literature, RAZ.

BTW, I don’t know how my karma is being calculated. My previous LW discussions were at the 1.0 version of the site where votes on posts counted for 10 karma, and votes on comments counted for 1 karma. When I went back the second time, a moderator boosted my karma enough to be positive so that I could write posts instead of just comments. LW 2.0 allows you to write posts while having negative karma and votes on posts and comments are worth the same amount, but your votes count for multiple karma if you have high karma and/or use the strong vote feature. I don’t know how old stuff got recalculated when they did the version 2.0 website.

Overall I have around negative 1 karma per comment, so that’s … not all that bad? Or apparently the lowest ever. If downvotes on the old posts still count 10x then hundreds of my negative karma is from just a few posts.

In general, I think outliers should be viewed as notable and potentially valuable, especially outliers that you can already see might actually be good (as habryka says about me below). Positive outliers are extremely valuable.

The biggest problem with his participation is that he has a history of dragging people into discussions that drag on for an incredibly long time, without seeming particularly productive, while also having a history of pretty aggressively attacking people who stop responding to him. On his blog, he and others maintain a long list of people who engaged with him and others in the Critical Rationalist community, but then stopped, in a way that is very hard to read as anything but a public attack. It's first sentence is "This is a list of ppl who had discussion contact with FI and then quit/evaded/lied/etc.", and in-particular the framing of "quit/evaded/lied" sure sets the framing for the rest of the post as a kind of "wall of shame".

I consider it strange to ban me for stuff I did in the distant past but was not banned for at the time.

I find it especially strange to ban me for 2 years over stuff that’s already 3 or 9 years old (the evaders guest post by Alan is a year old, and btw "evade" is standard Objectivist philosophy terminology). I already left the site for longer than the ban period. Why is a 5 year break the right amount instead of 3? habryka says below that he thinks I was doing better (from his point of view and regarding what the LW site wants) this time.

They could have asked me about that particular post before banning me, but didn’t. They also could have noted that it’s an old post that only came up because Andy linked it twice on LW with the goal of alienating people from me. They’re letting him get what he wanted even though they know he was posting in bad faith and breaking their written rules.

I, by contrast, am not accused of breaking any specific written rule that LW has, but I’ve been banned anyway with no warning.

Those three things in combination, a propensity for long unproductive discussions, a history of threats against people who engage with him, and being the historically most downvoted account in LessWrong history, make me overall think it's better for curi to find other places as potential discussion venues.

I didn’t threaten anyone. I’m guessing it was a careless wording. I think habryka should retract or clarify it. Above habryka used “attack[]” as a synonym for criticize. I don’t like that but it’s pretty standard language. But I don’t think using “threat[en]” as a synonym for criticize is reasonable.

“threaten” has meanings like “state one's intention to take hostile action against someone in retribution for something done or not done” and “express one's intention to harm or kill“ (New Oxford Dictionary). This is the one thing in the post that I strongly object to.

I do really want to make clear that this is not a personal judgement of curi. While I do find the "List of Fallible Ideas Evaders" post pretty tasteless, and don't like discussing things with him particularly much, he seems well-intentioned, and it's quite plausible that he could me an amazing contributor to other online forums and communities. Many of the things he is building over on his blog seem pretty cool to me, and I don't want others to update on this as being much evidence about whether it makes sense to have curi in their communities.

I do also think his most recent series of posts and comments is overall much less bad than the posts and comments he posted a few years ago (where most of his negative karma comes from), but they still don't strike me as great contributions to the LessWrong canon, are all low-karma, and I assign too high of a probability that old patterns will repeat themselves (and also that his presence will generally make people averse to be around, because of those past patterns). He has also explicitly written a post in which he updates his LW commenting policy towards something less demanding, and I do think that was the right move, but I don't think it's enough to tip the scales on this issue.

So I came back after 3 years, posted in a way they liked significantly better … I’m building cool things and plausibly amazing while also making major progress at compatibility with LW … but they’re banning me anyway, even though my old posts didn’t get me banned.

More broadly, LessWrong has seen a pretty significant growth of new users in the past few months, mostly driven by interest in Coronavirus discussion and the discussion we hosted on GPT3. I continue to think that "Well-Kept Gardens Die By Pacifism", and that it is essential for us to be very careful with handling that growth, and to generally err on the side of curating our userbase pretty heavily and maintaining high standards. This means making difficult moderation decision long before it is proven "beyond a reasonable doubt" that someone is not a net-positive contributor to the site.

In this case, I think it is definitely not proven beyond a reasonable doubt that curi is overall net-negative for the site, and banning him might well be a mistake, but I think the probabilities weigh heavily enough in favor of the net-negative, and the worst-case outcomes are bad-enough, that on-net I think this is the right choice.

I don’t see why they couldn’t wait for me to do something wrong to ban me, or give me any warning or guidance about what they wanted me to do differently. I doubt this would have happened this way if Andy hadn’t done targeted harassment.

At least they wrote about their reasons. I appreciate that they’re more transparent than most forums.

In another message, habryka clarified his comment about others not updating their views of me based on this ban:

The key thing I wanted to communicate is that it seems quite plausible to me that these patterns are the result of curi interfacing specifically with the LessWrong culture in unhealthy ways. I can imagine him interfacing with other cultures with much less bad results.

I also said "I don't want others to think this is much evidence", not "this is no evidence". Of course it is some evidence, but I think overall I would expect people to update a bit too much on this, and as I said, I wouldn't be very surprised to see curi participate well in other online communities.

I’m unclear on what aspect of LW culture that I’m a mismatch for. Or put another way: I may interface better with other cultures which have or lack what particular characteristics compared to LW?

---

Also, LW didn't explain how they decided on ban lengths. 2.3 year bans don't correspond to solving the problems raised. Andy or I could easily wait and then do the stuff LW doesn't want. They aren't asking us to do anything to improve or to provide any evidence that we've reformed in some way. Nor are they asking us to figure out how we can address their concerns and prevent bad outcomes. They're just asking us to wait and, I guess, counting on us not to hold grudges. Problems don't automatically go away due to time passing.

Overall, I think LW’s decision and reasoning are pretty bad but not super unreasonable. I wouldn’t expect better at most forums and I’ve seen much worse. Also, I’m not confident that the reasoning given fully and accurately represents the actual reasons. I'm not convinced that they will ban other people using the same reasoning like that they didn't break any particular rules but might be a net-negative for the site, especially considering that "the moderators of LW are the opposite of trigger-happy. Not counting spam, there is on average less than one account per year banned." (source from 2016, maybe they're more trigger-happy in 2020, I don't know).

This is Max's discussion thread. Max has agreed to only post as "Max" in this thread.

Here's the YouTube playlist where I tutor Max.

This is a thread for me to post stuff that's smaller than a blog post. You can reply and discuss here but don't start your own topics here. You can do that in Open Discussion or at any relevant post.

Eliezer Yudkowsky tweeted:

EY:

What on Earth is up with the people replying "billionaires don't have real money, just stocks they can't easily sell" to the anti-billionaire stuff? It's an insanely straw reply and there are much much better replies.

DL:

What would be a much better reply to give to someone who thinks for example that Elon Musk is hoarding $100bn in his bank account?

EY:

A better reply should address the core issue whether there is net social good from saying billionaires can't have or keep wealth: eg demotivating next Steves from creating Apple, no Gates vaccine funding, Musk not doing Tesla after selling Paypal.

Eliezer Yudkowsky (EY) frequently brings up names (e.g. Feynman or Jaynes) of smart people involved with science, rationality or sci-fi. He does this throughout RAZ. He communicates that he's read them, he's well-read, he's learned from them, he has intelligent commentary related to stuff they wrote, etc. He presents himself as someone who can report to you, his reader, about what those books and people are like. (He mostly brings up people he likes, but he also sometimes presents himself as knowledgeable about people he's unfriendly to, like Karl Popper and Ayn Rand, who he knows little about and misrepresents.)

EY is a liar who can't be trusted. In his tweets, he reveals that he brings up names while knowing basically nothing about them.

Steve Jobs and Steve Wozniak were not motivated by getting super rich. Their personalities are pretty well known. I guess EY never read any of the biographies and hasn't had conversations about them with knowledgeable people. Or maybe he doesn't connect what he reads to what he says. (I provide some brief, example evidence at the end of this post in which Jobs tells Ellison "You don’t need any more money." EY is really blatantly wrong.)

EY brings up Jobs and Wozniak ("Steves") to make his assertions sound concrete, empirical and connected to reality. Actually he's doing egregious armchair philosophizing and using counter examples as examples.

Someone who does this can't be trusted whenever they bring up other names either. It shows a policy of dishonesty: either carelessness and incompetence (while dishonestly presenting himself as a careful, effective thinker) or outright lying about his knowledge.

There are other problems with the tweets, too. For example, EY is calling people insane instead of arguing his case. And EY is straw manning the argument about billionaires having stocks not cash – while complaining about others straw manning. Billionaires have most of their wealth in capital goods, not consumption goods (that's the short, better version of the argument he mangled), and that's a more important issue than the incentives that EY brings up. EY also routinely presents himself as well-versed in economics but seems unable to connect concepts like accumulation of capital increasing the productivity of labor, or eating the seed corn, to this topic.

Some people think billionaires consume huge amounts of wealth – e.g. billions of dollars per year – in the form of luxuries or other consumption goods. Responding to a range of anti-billionaire viewpoints, including that one, by saying basically "They need all that money so they're incentivized to build companies." is horribly wrong. They don't consume anywhere near that much wealth per year. EY comes off as justifying them doing something they don't do that would actually merit concern if they somehow did it.

If Jeff Bezos were building a million statues of himself, that'd be spending billions of dollars on luxuries/consumption instead of production. That'd actually somewhat harm our society's capital accumulation and would merit some concern and consideration. But – crucial fact – the real world looks nothing like that. EY sounds like he's conceding that that's actually happening instead of correcting people about reality, and he's also claiming it's obviously fine because rich people love their statues, yachts and sushi so much that it's what inspires them to make companies. (It's debateable, and there are upsides, but it's not obviously fine.)

---

Steve Jobs is the authorized biography by Walter Isaacson. It says (context: Steve didn't want to do a hostile takeover of Apple) (my italics):

“You know, Larry [Ellison], I think I’ve found a way for me to get back into Apple and get control of it without you having to buy it,” Jobs said as they walked along the shore. Ellison recalled, “He explained his strategy, which was getting Apple to buy NeXT, then he would go on the board and be one step away from being CEO.” Ellison thought that Jobs was missing a key point. “But Steve, there’s one thing I don’t understand,” he said. “If we don’t buy the company, how can we make any money?” It was a reminder of how different their desires were. Jobs put his hand on Ellison’s left shoulder, pulled him so close that their noses almost touched, and said, “Larry, this is why it’s really important that I’m your friend. You don’t need any more money.”

Ellison recalled that his own answer was almost a whine: “Well, I may not need the money, but why should some fund manager at Fidelity get the money? Why should someone else get it? Why shouldn’t it be us?”

“I think if I went back to Apple, and I didn’t own any of Apple, and you didn’t own any of Apple, I’d have the moral high ground,” Jobs replied.

“Steve, that’s really expensive real estate, this moral high ground,” said Ellison. “Look, Steve, you’re my best friend, and Apple is your company. I’ll do whatever you want.”

(Note that Ellison, too, despite having a more money-desiring attitude, didn't actually prioritize money. He might be the richest man in the world today if he'd invested heavily in Steve Jobs' Apple, but he put friendship first.)

If you want to learn philosophy or rational thinking, you need to do some stuff on a regular basis. Read books, write notes, write outlines, write articles, write journaling, study stuff, have discussions, etc.

I suggest you write a short, weekly update. How did your week go? What did you do? Did you make progress on your goals? (Figure out some goals and write them down. If in doubt, talk about it or read and watch a wide variety of things.) Do you want to make any changes going forward? Sharing this update is optional. You could do it like journaling.

Write a longer, monthly update. Reflect more on how learning is going, what's working or not working, whether you should adjust any goals or stop or start any projects, what got done or not, etc.

Sharing monthly updates is recommended. If you don't share monthly updates or explain why not, I will not regard you as actually trying to learn philosophy.

I think it'd be best if a bunch of people shared monthly updates at the same time. So let's use the first of the month. Post them below. Put the month and your name in the title field when posting a monthly update, and leave the title blank for anything else, so the monthly updates stand out more.

Posting on your own website and sharing a link here is fine too. With the link, include at least one paragraph of text with some summary and some info to interest people in clicking the link.

I posted this on Less Wrong 10 days ago. At the end, I summarize the answer they gave.

---

What counts as a hypothesis for Solomonoff induction? The general impression I’ve gotten in various places is “a hypothesis can be anything (that you could write down)”. But I don’t think that’s quite it. E.g. evidence can be written down but is treated separately. I think a hypothesis is more like a computer program that outputs predictions about what evidence will or will not be observed.

If X and Y are hypotheses, then is “X and Y” a hypothesis? “not X”? “X or Y?” If not, why not, and where can I read a clear explanation of the rules and exclusions for Solomonoff hypotheses?

If using logic operators with hypotheses does yield other hypotheses, then I’m curious about a potential problem. When hypotheses are related, we can consider what their probabilities should be in more than one way. The results should always be consistent.

For example, suppose you have no evidence yet. And suppose X and Y are independent. Then you can calculate the probability of P(X or Y) in terms of the probability of P(X) and P(Y). You can also calculate the probability of all three based on their length (that’s the Solomonoff prior). These should always match but I don’t think they do.

The non-normalized probability of X is 1/2^len(X).

So you get:

P(X or Y) = 1/2^len(X) + 1/2^len(Y) - 1/2^(len(X)+len(Y))

and we also know:

P(X or Y) = 1/2^len(X or Y)

since the left hand sides are the same, that means the right hand sides should be equal, by simple substitution:

1/2^len(X or Y) = 1/2^len(X) + 1/2^len(Y) - 1/2^(len(X)+len(Y))

Which has to hold for any X and Y.

We can select X and Y to be the same length and to minimize compression gains when they’re both present, so len(X or Y) should be approximately 2len(X). I’m assuming a basis, or choice of X and Y, such that “or” is very cheap relative to X and Y, hence I approximated it to zero. Then we have:

1/2^2len(X) = 1/2^len(X) + 1/2^len(X) - 1/2^2len(X)

which simplifies to:

1/2^2len(X) = 1/2^len(X)

Which is false (since len(X) isn’t 0). And using a different approximation of len(X or Y) like 1.5len(X), 2.5len(X) or even len(X) wouldn’t make the math work.

So Solomonoff induction is inconsistent. So I assume there’s something I don’t know. What? (My best guess so far, mentioned above, is limits on what is a hypothesis.)

Also here’s a quick intuitive explanation to help explain what’s going on with the math: P(X) is both shorter and less probable than P(X or Y). Think about what you’re doing when you craft a hypotheses. You can add bits (length) to a hypothesis to exclude stuff. In that case, more bits (more length) means lower prior probability, and that makes sense, because the hypothesis is compatible with fewer things from the set of all logically possible things. But you can also add bits (length) to a hypothesis to add alternatives. It could be this or that or a third thing. That makes hypotheses longer but more likely rather than less likely. Also, speaking more generally, the Solomonoff prior probabilities are assigned according to length with no regard for consistency amongst themselves, so its unsurprising that they’re inconsistent unless the hypotheses are limited in such a way that they have no significant relationships with each other that would have to be consistent, which sounds hard to achieve and I haven’t seen any rules specified for achieving that (note that there are other ways to find relationships between hypotheses besides the one I used above, e.g. looking for subsets).

---

Less Wrong's answer, in my understanding, is that in Solomonoff Induction a "hypothesis" must make positive predictions like "X will happen". Probabilistic positive predictions – assigning probabilities to different specific outcomes – can also work. Saying X or Y will happen is not a valid hypothesis, nor is saying X won't happen.

This is a very standard trick by so-called scholars. They take a regular English word (here "hypothesis") and define it as a technical term with a drastically different meaning. This isn't clearly explained anywhere and lots of people are misled. It's also done with e.g. "heritability".

Solomonoff Induction is just sequence prediction. Take a data sequence as input, then predict the next thing in the sequence via some algorithm. (And do it with all the algorithms and see which do better and are shorter.) It's aspiring to be the oracle in The Fabric of Reality but worse.

RSS feeds let you get updates when a website has new stuff. You can subscribe to sites you're interested in and then get notifications about new material instead of checking for it yourself. This works especially well with sites that don't update often.

You should subscribe to my feeds:

• curi.us posts
• curi.us comments
• curi YouTube videos
• Fallible Ideas Podcast

You need an RSS Reader app. I like Vienna, a free open source Mac app. There are many others, e.g. BazQux is a web app that my friend likes.

Many apps will let you import RSS feeds instead of adding them all yourself. Download my subscriptions to import. After importing, you can delete whatever you don't want.

You should also sign up for my free email newsletter. I'll send you around one email every two weeks.

Most blogs and similar sites have RSS feeds. Usually you can use their home page and the RSS app will find the correct feed URL for you. You can also subscribe to a YouTube channel or podcast.

Don't rely on getting all your info from social media sites. Don't just read whatever's in your Facebook, Twitter or Reddit feed. Choose and subscribe to some sites yourself.