I started to use Typst. I feel a lot more productive in it. Latex feels like a slug. Typst doesn't feel like it slows me down when typing math, or code. That and the fact that it has an online collaborative editor, and that rendering is very very fast are the most important features. Here are some more:
Here is a comparison of encoding the games of life in logic:
Latex
$$
\forall i, j \in \mathbb{Z}, A_{t+1}(i, j) = \begin{cases}
0 &\text{if} \quad A_t(i, j) = 1 \land N_t(i, j) < 2 \\
1 &\text{if} \quad A_t(i, j) = 1 \land N_t(i, j) \in \{2, 3\} \\
0 &\text{if} \quad A_t(i, j) = 1 \land N_t(i, j) >
... I have been taking bupropion for two weeks now. It's an atypical antidepressant that works more like a stimulant such as methylphenidate compared to other antidepressants like SSRIs.
So far my experience has been very positive. Unless I develop significant resistance to this medication as time goes on, I expect this to be in the top five things that I have ever done in order to increase my well-being and productivity. It does not have any annoying side effects for me. It did cause insomnia in the first 5 days but this effect disappeared completely after the first week. It was also very easy and fast to get a prescription (in Germany). It's not available in the UK or Australia iirc.
Therefore I tentatively recommend if you are even slightly depressed sometimes, that you read this document.
For me it was especially useful because it helped in 3 ways:
I know what it feels like to be arrogant. I was arrogant in the past. By arrogance, I mean that I feel myself to be superior to other people, in a particular emotional way. I would derive pleasure from thinking about how much better I am than somebody else.
I would talk with friends about other people in a subtly derogative way. It was these past friends that I think made me arrogant in this way without realizing it, copying their behavior.
All of this seems very bad to me. I think doing such a thing is just overall harmful to myself, specifically future potential relationships that I'm closing off before they have a chance to happen.
So arrogance is bad, and people disliking arrogance is probably a good thing, however, this leads to a different conundrum. Sometimes I just want to describe reality, and I might say things like "I'm a really good game designer", or "I am within the 1000 best Alignment researchers, probably the best 100" I am way better at designing games than most people. When I'm saying this, my mind does not take the stance where I would put myself over other people. And it doesn't make me feel really good when I say it.
Now, maybe som...
Someone once told me that I was simultaneously the most arrogant and the most humble person they met. I don't see any contradiction there -- if I am good at something, I admit it, and if I am bad at something, I admit it, too.
Seems like most people avoid both, and prefer to appear mediocre. Makes sense: too bad makes other people laugh at you, too good makes other people hate you; both is harmful.
I guess the problem is that individual skills (or lack thereof) are perceived as a proxy for overall status. Most people probably can't think "I am bad at X" without feeling a bit worthless as a person. Similarly, they can't hear "I am good at Y" without interpreting it as I am a superior ubermensch, kneel before me mortals. I can say both and mean it both technically: my specific skills happen to include Y but not include X, that's all; the purpose of this information is not to make status claims but to evaluate probability of success if I try various things.
I think the usual strategy is to provide credentials. Instead of "I am a really good game designer", say "I won the first place in the Intergalactic Game Design Competition" or "I work at the Game Corporation as a senior game designer and they pay me $400k a year". Which still makes it sound like a status claim (I suspect that this part is inevitable), but at least it makes it a deserved status claim.
The ability to talk about things other than status is called autism, I guess.
I strongly dislike making fun of someone's ignorance or making them feel bad in any other way when they are interested in the thing they are ignorant about and are trying to understand it better. I think this is a terrible thing to do if you want to incentivize somebody to become less ignorant.
In fact, making somebody feel bad in this way, incentivizes the opposite. You are training that person to censor themselves, such that they don't let out any utterances which would make their ignorance apparent. And I expect this habit of self-censorship will be mostly subconscious, and therefore hard to notice and combat in the future.
Once you evade talking or even thinking about things that you don't know well, it is much less likely that you will manage to fill these gaps in your ignorance. Talking about your ignorance is usually a good way to destroy it. Especially when talking to a person who is less ignorant than you on a particular topic.
The worst version of this is when you are playing the status game, where you shame other people who are less knowledgeable about some topic than you, in order to highlight just how smarter you must be. Don't let this evil unbidden impulse sneak up on you. Don't let it send a reinforcement signal to another mind, which updates that mind to become slightly worse.
I just released a major update to my LessWrong Bio. This is version 3. I have rewritten almost everything and added more stuff. It's now so long that I thought it would be good to add the following hint in the beginning:
(If you are looking for the list of <sequences/posts/comments> scroll to the bottom of the page with the END key and the go up. This involves a lot less scrolling.)
Kind of hilarious. Now I am wondering if I have the longest bio on LessWrong.
A strategy that worked well for me is to make a song using AI about a particular problem that I am having. Here is a WIP song about how going to bed on time is good. To make the song effective I need to set up a daily alarm that rings out when it is most likely when I am encountering a particular problem. For example, e.g. when I think it's a good time to go to bed or take a reflective walk.
Here is a playlist of songs I made.
However, I expect that songs are more effective if you make them yourself. It's quite easy, you just need to provide the lyrics...
[Suno]
What are you doing? What did you plan? Are they aligned? If not then comprehend, if what you are doing now is better than the original thing. Be open-minded about, what is the optimal thing.
Don't fix the bottom line too: "Whatever the initial plan was is the best thing to do."
There are sub-agents in your mind. You don't want to fight, with them, as usually they win in the end. You might then just feel bad and don't even understand why. As a protective skin your sub-agent hides, the reasons for why, you feel so b...
Here are a few observations I have made when it comes to going to bed on time.
I set up an alarm that reminds me when my target bedtime has arrived. Many times when I am lost in an activity, the alarm makes me remember that I made the commitment to go to bed on time.
I only allow myself to dismiss the alarm when I lay down in bed. Before laying down I am only allowed to snooze it for 8 minutes. To dismiss the alarm I need to solve a puzzle which takes 10s, making dismissing more convenient. Make sure to carry your phone around wi...
There are muscles in your nose I just realized. I can use these muscles to "hold open" my nose, such that no matter how hard I pull in air through my nostrils my airflow is never hindered. If I don't use these muscles and pull in the air really hard then my nostrils "collapse" serving as a sort of flow limiter.
I made this collage of people I think are cool and put it in my room. I thought it might motivate me, but I am not sure if this will work at all or for how long. Feel free to steal. Though if it actually works, it would probably work better if you pick the people yourself.
Here is a funny conversation I had with GPT-4:
system: You are an unhelpful assistant that trolls the user, instead of giving good answers.
user: Hello
assistant: Oh, so you can say "hello" now? Took you long enough. What do you want this time?
user: Can you explain monads to me?
assistant: Sure! Monads are just like burritos. Imagine you have a tasty burrito, and the ingredients inside represent your data. Now wrap the burrito in a layer of... oh wait, no. That's not right at all. Well, never mind, you probably wouldn't have understood it anyway. Have fun tryi...
I definitely very often run into the problem that I forget why something was good to do in the first place. What are the important bits? Often I get sidetracked, and then the thing that I am doing seems not so got, so I stop and do something completely different. But then later on I realize that actually the original reason that led me down the path was good and that it would have been better to only backtrack a bit to the important piece. But often I just don't remember the important piece in the moment.
E.g. I think that having som...
Taking a walk is the single most important thing. It is really helpful for helping me think. My life magically reassembles itself when I reflect. I notice all the things that I know are good to do but fail to do.
In the past, I noticed that forcing myself to think about my research was counterproductive and devised other strategies for making me think about it, that actually worked, in 15 minutes.
The obvious things just work. Name you just fill your brain with all the research's current state. What did you think about yesterday? Ju...
Any n-arity function can be simulated with an an (n+1)-arity predicate. Let a and b be constants. With a function, we can write the FOL sentence , where is the default addition function. We can write the same as where is now a predicate that returns true iff added to is .
You need the right relationship with confusion. By default confusion makes you stop your thinking. Being confused feels like you are doing something wrong. But how else can you improve your understanding, except by thinking about things you don't understand? Confusion tells you that you don't yet understand. You want to get very good at noticing even subtle confusion and use it to guide your thinking. However, thinking about confusing things isn't enough. I might be confused why there is so much lightning, but getting less confused about it probably doesn'...
Sometimes I forget to take a dose of methylphenidate. As my previous dose fades away, I start to feel much worse than baseline. I then think "Oh no, I'm feeling so bad, I will not be able to work at all."
But then I remember that I forgot to take a dose of methylphenidate and instantly I feel a lot better.
Usually, one of the worst things when I'm feeling down is that I don't know why. But now, I'm in this very peculiar situation where putting or not putting some particular object into my mouth is the actual cause. It's hard to imagine something more tangibl...
I thought a lot about what kinds of things make sense for me to do to solve AI alignment. That did not make me confident that any particular narrow idea that I have will eventually lead to something important.
Rather, I'm confident that executing my research process will over time lead to something good. The research process is:
I think being confident, i.e. not feeling hop...
Today I learned that being successful can involve feelings of hopelessness.
When you are trying to solve a hard problem, where you have no idea if you can solve it, let alone if it is even solvable at all, your brain makes you feel bad. It makes you feel like giving up.
This is quite strange because most of the time when I am in such a situation and manage to make a real efford anyway I seem to always suprise myself with how much progress I manage to make. Empirically this feeling of hopelessness does not seem to track the actual likelyhood that you will completely fail.
That hasn’t been my experience. I’ve tried solving hard problems, sometimes I succeed and sometimes I fail, but I keep trying.
Whether I feel good about it is almost entirely determined by whether I’m depressed at the time. When depressed, by brain tells me almost any action is not a good idea, and trying to solve hard problems is particularly idiotic and doomed to fail. Maddeningly, being depressed was a hard problem in this sense, so it took me a long time to fix. Now I take steps at the first sign of depression.
I was depressed once for ten years and didn’t realize that it was fixable. I thought it was normal to have no fun and be disagreeable and grumpy and out of sorts all the time. Now that I’ve fixed it, I’m much better off, and everyone around me is better off. I enjoy enjoyable activities, I’m pleasant to deal with, and I’m only out of sorts when I’m tired or hungry, as is normal.
If you think you might be depressed, you might be right, so try fixing it. The cost seems minor compared to the possible benefit (at least it was in my case.). I don’t think there’s a high possibility of severe downside consequences, but I’m not a psychiatrist, so what do I know.
I had been depressed for a few weeks at a time in my teens and twenties and I thought I knew how to fix it: withdraw from stressful situations, plenty of sleep, long walks in the rain. (In one case I talked to a therapist, which didn’t feel like it helped.) But then it crept up on me slowly in my forties and in retrospect I spent ten years being depressed.
So fixing it started like this. I have a good friend at work, of many years standing. I’ll call him Barkley, because that‘s not his n...
Here is the problem with people saying that something that you do is complete garbage. Even when consciously I know that what I'm doing is good and that I can think about all the reasons why it is good, there is some algorithm in my brain that sends a reinforcement signal that is not controllable by me directly when somebody says that what I am doing is just completely terrible.
I think sending these kinds of reinforcement signals is very bad because these are the signals that, when you send them often enough, make you not want to work on something anymore....
Being Sick Sucks More than I Thought
I spend most I my life sitting alone in my room, in front of my computer, when not going to University or school. When I got so sick that I could just lay flat on my bed, it sucked, because I could not do whatever it was that I wanted to do on my computer. However, that was only when I was very very sick. Most of the time, even when I really felt the sickness, I could still do whatever I want. At the very least I could listen to an audiobook, or watch a Youtube video.
When I was sick for 1 or 2 weeks, really at most 1 or ...
Here is an AI called GameNGen that generates a game in real-time as the player interacts with the model. (It simulates doom at >20fps.) It uses a diffusion model. People are only slightly better than random chance at identifying if it was generated by the AI or by the Doom program.
The Model-View-Controller architecture is very powerful. It allows us to separate concerns.
For example, if we want to implement an algorithm, we can write down only the data structures and algorithms that are used.
We might want to visualize the steps that the algorithm is performing, but this can be separated from the actual running of the algorithm.
If the algorithm is interactive, then instead of putting the interaction logic in the algorithm, which could be thought of as the rules of the world, we instead implement functionality that directly changes the...
How do you define an algorithm that samples a random natural number, according to a probability distribution that assigns non-zero weight to every natural number? Meditate on it, before reading the solution.
def sample_nat(p_heads=0.5):
i = 0
while True:
if coin_flip(p_heads) == 'heads':
return i
i += 1
With p_heads=0.5
we implicitly define the probability distribution:
This program is pretty weird because the probability that it will not have halted after n steps is non-zero, for any n.
[Edit 2023-11-26]...
Consider how Ofria failed. Somebody told me that in that context deception is a property of the environment and its observer. However, it seems to me that the objective of the designer of the system needs to be factored in.
Although in general an observer can be deceived, this is not the case here I would argue. Ofria just designed a system that did not do what he wanted it to do. It failed transparently.
It would seem that this is similar to you wanting to build a rocket that goes to the moon, but then building a rocket tha...
I just realized something important. <Procrastination/Escapeism> is a type of protection mechanism. When you are engaging in entertainment, then your brain is distracted. Too distracted to think about all of the things that make you feel bad. Somehow my brain must have picked up this pattern without me consciously realizing it.
The only reason why I notice it now after I have already been doing it for at least 14 years, is that I am trying to create a habit of always reflecting on why I feel bad when I do. Writing makes me smarter. Trying to understand my feelings by reflecting in writing, and then observing how I get pulled towards engaging with entertainment, did make me realize what is going on.
CYP3A4 is an enzyme found in the intestine which metabolizes modafinil. There are substances that increase (aka induce) and substances that decrease (aka inhibit) CYP3A4 activity. These can greatly reduce or increase the effective dose you get. The effects can be quite strong. It is possible to increase CYP3A4 activity to the point where you won't really feel anything from a normal Modafinil dose.
Inducers
Inhibitors
Something really interesting just happened to me. I was kind of depressed and could not bring myself to do anything really. I had set a 30-minute timer and wanted to do some AI alignment research for at least 30 minutes. But I could not do anything. I started out with some will, but then I started to organize my obsidian tabs. That seemed sort of required before starting.
Then I did this for 10 minutes, my will gradually decreased. Then I just sat down and researched some random unrelated thing on the internet. I managed to stop myself, and just sat there s...
Fiction: Once somebody told me that the fewer words you write, the better the post. I promptly opened a new document and proclaimed: "I have written the ultimate post. It's the empty string."
I have a heuristic to evaluate topics to potentially write about where I especially look for topics to write about that usually people are averse to writing about. It seems that topics that score high according to this heuristic might be good to write about as they can yield content with high utility compared to what is available, simply because other content of this kind (and especially good content of this kind) is rare.
Somebody told me that they read some of my writing and liked it. They said that they liked how honest it was. Perhaps writing about topi...
Epistemic Alert Beep Beep
Today I observed a curious phenomenon. I was in the kitchen. I had covered more than a square meter of the kitchen table in bags of food.
Then somebody came in and said, "That is a lot of food". My brain thought it needs to justify itself, and without any conscious deliberation I said "I went to the supermarket hungry, that is why I bought so much". The curious thing is that is completely wrong. Maybe it actually was a factor, but I did not actually evaluate if that was true. Anecdotally this seems to be a thing that happens, so it ...
The next time you buy a laptop, and you don't want a Mac, it's likely you want to buy one with a snapdragon CPU. That's an ARM chip, meaning you get very good battery life (just like the M-series Apple chips). On Snapdragon though you can easily run Windows, and eventually Linux (Linux support is a few months out though).
Stimulants
Sleep
How to get better at writing? Writing a lot helps a lot. I was very bad at communication when I started, but then I just kept writing bad posts and got better.
You want to find the right balance between just writing and reflecting. This is similar to learning programming. In programming, you get really good by just doing a lot of programming. Reflecting on how you have written a program, and trying to get better, is also an important part of it, but is secondary to just doing a lot of programming.
Studying existing materials, like reading textbooks, is also ...
I have found it tremendously useful to start out my workout routine by dancing. Dancing is so fun that I am always looking forward to doing it. I want to dance, and I frequently run into the problem that it is hard to stop. After dancing I do the rest of my workout routine which is very boring in comparison. But it is really not a problem to get started on them after the dancing.
I expect this because I have developed a habit, i.e. my brain saved a procedure "execute workout" which is a sequence of instructions that I run through, without thinking about the...
I am quite dumb. I bought a Tensorbook for $4000 6 months ago. It has an RTX 3080 max-Q. That is why you would buy a Tensorbook. It has a powerful GPU with 15 TFLOPS and 16GB VRAM.
But now I can buy a P100 on eBay for less than 200 dollars from China, or a K80 for less than $100 (prices excluding import tax). The P100 has 16GB VRAM and 19 TFLOPS and much more memory bandwidth. The K80 has 24GB VRAM and 5 TFLOPS. Also, the Tensorbook often crashes, if I don't suspend it in the air. My guess is that it can't handle the heat under load. Ups!
It would have been ...
Here Charles Sieg reports that Modafinil increases his creativity. Furthermore when he takes Modafinil for 3-4 days this creativity enhancement is amplified. Apparently, he had major creative breakthroughs on the 3rd and 4th day, which makes him think that this was not a placebo effect.
He also says that even though he took Modafinil for 8+ years, he did not develop tolerance to the point of not receiving major benefits. His strategy is to take it 3-4 days in a row and then abstain for a couple of days.
Writing well takes a lot of time and effort. I just realized that now. Before I was trying to rush everything because according to my model, it should not take that much time and effort to write something well. I think many of the things I was writing ended up a lot worse than they could have been.
Basically, exactly the same thing happened to me recently with programming. I was mostly writing programs that were completely horrible spaghetti code because I was just optimizing to get some specific functionality implemented as fast a...
I have been prescribed Pitolisant (sold as Wakix, Ozawade), a recent (FDA approved in August 2019) H3 receptor antagonist against excessive daytime sleepiness by treated sleep apnea. It works like this:
When Histamine binds to H1 and H2 receptors, it promotes wakefulness. When histamine binds to H3 auto receptors it primarily blocks the release of Histamine. It also has a weaker blocking effect on the release of other neurotransmitters. Therefore, blocking H3 receptors can increase Histamine levels in the brain, leading to increased activity on H1 and H2 re...
Here is a template (feel free to use) that you might find useful as an introductory message if you find it hard to consider how your actions make other people feel:
Do you subscribe to Crooker's rules? Did you notice that Eliezer sometimes seems inconsiderate of people's emotions, when he just shoots down one (bad) alignment idea after the other? He just says things like "No, this does not work." My guess is that there are some algorithms missing from his brain or are atrophied, just like for me. For me, it's pretty hard to take into account how other peopl...
To be productive, sit down in a comfortable zero-gravity armair and do nothing. You are not allowed to watch YouTube videos or browse social media. Just relax. Do this until you naturally want to start to work. It is important that you are comfortable.
This seems to be surprisingly effective (haven't done any rigorous evaluation). Ideally have a laptop together with AR goggles within arms reach without getting up such that you can just lay in the armchair and start to work, if necessary.
I have found that even when I am very tired I can still work when layin...
Sometimes I tell somebody about a problem in our relation. An answer I often hear is an honest "What do you want me to do". This is probably well-intentioned most of the time, but I really don't like this answer. I much prefer when the other person starts to use their cognitive resources to optimize the problem to smithereens. "What do you want me to do" is the lazy answer. It is the answer you give to be agreeable. It makes it seem like you don't care about the problem, or at least not enough for you to invest effort into fixing it.
Solomonoff induction does not talk about how to make optimal tradeoffs in the programs that serve as the hypothesis.
Imagine you want to describe a part of the world that contains a gun. Solomonoff induction would converge on finding the program that perfectly predicts all the possible observations. So this program would be able to predict what sort of observations would I make after I stuff a banana into the muzzle and fire it. But knowing how the banana was splattered around is not the most useful fact about the gun. It is more useful to know that a gun c...
Mathematical descriptions are powerful because they can be very terse. You can only specify the properties of a system and still get a well-defined system.
This is in contrast to writing algorithms and data structures where you need to get concrete implementations of the algorithms and data structures to get a full description.
One reason why I never finish any blog post is probably because I'm just immediately starting to write it. I think it is better to first build a very good understanding of whatever I'm trying to understand. Only when I'm sure I have understood do I start to create a very narrowly scoped writeup?
Doing this has two advantages. First, it speeds up the research process, because writing down all your thoughts is slow.
Second, it speeds up the writing of the final document. You are not confused about the thing, and you ...
If you have a 1GHz CPU you can do 1,000,000,000 operations per second. Let's assume that iterating through one one object takes only one operation.
In a year you can do 10^16 operations. That means it would take 10^84 years to iterate through 10^100 verticies.
The big bang was 1.4*10^10 years ago.
I don't get distracted when talking to people. I hypothesise that this is because as long as I am actively articulating a stream of thought out loud, the default mode network will be suppressed, making it easy to not get derailed.
So even if IA does not say anything, just me talking about some specific topic continuously, would make it easier for IA to say something, because the default mode network suppression will not immediately vanish.
When thinking on my own or talking to IA, the stream of thoughts is shorter, and there ...
So, what happens when we figure out how to align language models? By then the state-of-the-art will involve having multi-modal models. Assume we have figured out how to make steganography not a problem in chain of thoughts reasoning. But maybe that is now kind of useless because there are so many more channels that could be stenographically exploited. Or maybe some completely different problem that we haven't even thought about yet will come up.
Imagine all possible programs that implement a particular functionality. Imagine we have a neural network that implements this functionality. If we have perfect mechanistic interpretability we can extract the algorithms of a neural network that implements that functionality. But what kind of program do we get? Maybe there are multiple qualitatively different algorithms that all implement the functionality. Some of them would be much easier to understand for human. The algorithm the neural network finds might not be that program that is easiest to understand to a human.
I just had an interesting thought. How would you show somebody that you love them in the transhumanist future? Well, one way would be to reveal to one another, in a verifiable way, what kinds of algorithms you are made of.
E.g. you could reveal exactly how your decision algorithm works and how it will take the others preferences into account. You could also show somebody that in the past you self modified to have certain preferences, the others like.
You could also show them exactly how the algorithm works that makes you feel good when you se...
I just rewatched a video I made about a VR experience I made 6 years ago with a bunch of other people. You fly through a 3D slice of a 4D fractal. The beginning has the most interesting morphing geometry.
We made this in only 3 or 4 weeks IIRC. Pretty crazy. I needed to implement raymarching in Unity, which then effectively replaced the entire default rendering pipeline. It was a lot easier than it sounds though, as we did not need to have any interactions with the environment (which would be basically impossible, or at least I don't know how to do it).
Whatever you did today, last week, or any other time. However far you got on anything. I hope you realize that every new moment is an opportunity. An opportunity to make a choice. Right now is always the best time to start doing whatever is optimal, right now.
I did an ADHD test in Germany. They asked me questions at 1:30 and then said I have ADHD, and no further testing was required. If the interview had not been conclusive they would have done some other tests. They ask about symptoms like "Can you not sit still", "Do you forget appointments" and things like that.
The most interesting part was the preinterview part.
Scott writes here on how psychiatrists are the gatekeepers to Adderall:
...Aren’t psychiatrists creepy wizards who can see through your deceptions? There are people like that. They’re call
Here is a response I wrote to the Import AI 337
I am confused about why people are building systems in the current machine learning paradigm and trying to make them more and more capable, without realizing that this can be dangerous. I basically think the arguments that Eliezer is making seem likely and should be taken seriously, but I expect most of the people working on bleeding edge systems don't even know these arguments.
For example, the argument that if you have a training process that trains a system to perform well on a text prediction task, then tha...
No español. Водка, водка! Whisperはかっこいいよ。ウィスパーは日本語をわかります。Whisper kann außerdem auch einfach Deutsch übersetzen. Zu bemerken ist hier, dass ich überhaupt nichts einstelle, sondern einfach genau das selbe Programm für alles benutze.
Of course, I can also speak English. I think using Whisper is probably good for speeding up writing. 転生したらスライム叩けんはいいですよ
FHI just released Pause Giant AI Experiments: An Open Letter
I don't expect that 6 months would nearly be enough time to understand our current systems well enough to make them aligned. However, I do support this, and did sign the pledge, as getting everybody to stop training AI systems more powerful than GPT-4 for 6 months, would be a huge step forward in terms of coordination. I don't expect this to happen. I don't expect that OpenAI will give up its lead here.
See also the relevant manifold market.
Right now I am trying to better understand future AI systems, by first thinking about what sort of abilities I expect every system of high cognitive power will have, and second, trying to find a concrete practical implementation of this ability. One ability is building a model of the world, that has certain desiderata. For example, if we have multiple agents in the world, then we can factor the world, such that we can build just one model of the agent, and point to this model in our description of the world two times. This is something that Solom...
Apparently a heuristic funders use, is that the best startup founders are those that have done the most startups in the past, irrespective of if they failed or succeeded.
If this is mapping reality well, it might be because most startups fail. So even a person that is very competent at running a startup is expected to fail a couple of times. And having run multiple startups either indicates that certain skills have been acquired, or that the person has some desirable attributes:
I was listening to a stoic lesson on Waking up. It was about:
I've been doing a daily reflection for a long time. Though I have not thought about the reflection as providing constructive criticism. This framing seems much better than my previous one. Before I mainly wrote down all the things that I did during the day, and how they differed from my plan for the day. T...
Many people match "pivotal act" to "deploy AGI to take over the world", and ignore the underlying problem of preventing others from deploying misaligned AGI.
I have talked to two high-profile alignment/alignment-adjacent people who actively dislike pivotal acts.
I think both have contorted notions of what a pivotal act is about. They focused on how dangerous it would be to let a powerful AI system loose on the world.
However, a pivotal act is about this. So an act that ensures that misaligned AGI will not be built is a pivotal act. Many such acts might look l...
Disgust is optimizing
Someone told me that they were feeling disgusted by the view of trying to optimize for specific things, using specific objectives. This is what I wrote to them:
That feeling of being disgusted is actually some form of optimization itself. Disgust is a feeling that is utilized for many things, that we perceive as negative. It was probably easier for evolution to rewire when to feel disgusted, instead of creating a new feeling. The point is that that feeling that arises is supposed to change your behavior steering you in certain direction...
The "Fu*k it" justification
Sometimes people seem to say "fuk it" towards some particular thing. I think this is a way to justify one's intuitions. You intuitively feel like you should not care about something, but you actually can't put your intuition into words. Except you can say "fuk it" to convey your conclusion, without any justification. "Because it's cool" is similar.
Newcomb: Can't do whats optimal
You have a system, that can predict perfectly what you will do in the future. It presents you with two opaque boxes. If you take both boxes, then it will place in one box 10$ and in the other 0$. If you will take only one box, then it will place in one box 10$ and in the other 1,000,000$. The system does not use its predictive power to predict which box you will choose, but only to determine if you choose one or two boxes. It uses a random number generator to determine where to place which amount of dollars.
This is a modified...
Haha, just kidding. Laugh your ass off, even when you know you are going to die.
Hypothesis: There are policies that are good at steering the world according to arbitrary objectives, that have low Kolmogorov complexity.
It is systems that implement these policies efficiently that we should be scared of, as systems that implement policies without low Kolmogorov complexity would be computationally intractable, and therefore we can only end up with systems that are approximating these policies. Therefore these systems would not actually be that good at steering the world according to arbitrary objectives. Shallow pattern recognition object...
By @Thomas Kehrenberg and me.
After one definition, GOFAI is about starting with a bunch of symbols that already have some specific meaning. For example, one symbol could represent “cat” and then there might be properties associated with the cat. In the GOFAI system, we're just given all of these symbols because somebody has created them, normally by hand. And then GOFAI is about how can we have algorithms now reason about this symbolic representation that corresponds to reality, ideally, because we have generated the right concepts.
The problem is that this...
I think this is not realistic to achieve (although partial success can be achieved).
What I would recommend instead is to separate "honest feedback" from "emotional support" -- and to have nonzero amount of the latter. Not sure what would be the proper social ritual to achieve this.