LESSWRONG
LW

All of daijin's Comments + Replies

help, my self image as rational is affecting my ability to empathize with others

Answer by daijinMar 03, 202570

go find people who are better than you by a lot. one way to quickly do this is to join some sort of physical exercise class e.g. running, climbing etc. there will be lots of people who are better than you. you will feel smaller.

or you could read research papers. or watch a movie with real life actors who are really good at acting.

you will then figure out, as @Algon has mentioned in the comments, that the narcissism is load-bearing, and have to deal with that. which is a lot more scary

Will_Pearson's Shortform

daijin11d10

game-theory-trust is built through expectation of reward from future cooperative scenarios. it is difficult to build this when you 'dont actually know who or how many people you might be talking to'.

1Will_Pearson11d

True, I was thinking there would be gates to participation in the network that would indicate the skill or knowledge level of the participants without indicating other things about their existence. So if you put gates/puzzles in their way s to participation uch that only people that could generate reward you if they so choose to cooperate could pass it, that would dangle possible reward in front of you.

Intellectual lifehacks repo

daijin12d11

I did see the XKCD and I agree haha, I just thought your phrasing implied 'optimize everything (indiscriminately)'.

When I say caching I mean retaining intermediate results and tools if the cost to do so is near free.

groblegark's Shortform

daijin13d10

Nice. So something like grabbing a copy of swebench dataset, writing a pipeline that would solve those issues, then putting that on your CV?

I will say though that your value as an employee is not 'producing software' so much as solving business problems. How much conviction do you have that producing software marginally faster using AI will improve your value to your firm?

2groblegark13d

I think part of the important part is building your own (company's) collection of examples to train against, since the foundation models are trained against swebench already. And if it works the advantage would be on my CV in the worst case but in equity appreciation in the best case. So, just like any skill, right? You're right that the whole thing only works if the business can generate returns to high quality code, and can write specifications faster than its complement of engineers can implement them. But I've been in that position several times, it does happen. Mainly when the core functionality of the product is designed and led by domain experts who are not software engineers. Like if you make software for accountants for instance.

ank's Shortform

daijin13d50

so you want to build a library containing all human writings + an AI librarian.

the 'simulated planet earth' is a bit extra and overkill. why not a plaintext chat interface e.g. what chatGPT is doing now?
of those people who use chatgpt over real life libraries (of course not everyone), why don't they 'just consult the source material'? my hypothesis is that the source material is dense and there is a cost to extracting the desired material from the source material. your AI librarian does not solve this.

I think what we have right now ("LLM assistants that ar... (read more)

1ank13d

Thank you, daijin, you have interesting ideas! The library metaphor is a versatile tool it seems, the way I understand it: My motivation is safety, static non-agentic AIs are by definition safe (humans can make them unsafe but the static model that I imply is just a geometric shape, like a statue). We can expose the library to people instead of keeping it “in the head” of the librarian. Basically this way we can play around in the librarian’s “head”. Right now mostly AI interpretability researchers do it, not the whole humanity, not the casual users. I see at least a few ways AIs can work: 1. The current only way: “The librarian visits your brain.” Sounds spooky but this is what is essentially happening right now to a small extent when you prompt it and read the output (the output enters your brain). 2. “The librarian visits and changes our world.” This is where we are heading with agentic AIs. 3. New safe way: Let the user visit the librarian’s “brain” instead, make this “brain” more place-like. So instead of the agentic librarians intruding and changing our world/brains, we’ll intrude and change theirs, seeing the whole content of it and taking into our world and brain only what we want. I wrote more about this in the first half of this comment, if you’re interested Have a nice day!

Weirdness Points

daijin13d10

Another consequence of this is that inviting your friend to zendo is not weird, but inviting all your friends publically to zendo is.

Weirdness Points

daijin13d1-1

'Weirdness' is not about being other from the group, it is about causing the ingroup pain, which happens to correlate to being distinct from the ingroup (weird). We should call them ingroup-pain-points.

Being loudly vegan is spending ingroup-pain-points, because being in front of someone's face and criticising their behaviour causes them pain. Serving your friends tasty vegan food does not cause them pain and therefore incurs no ingroup-pain-points.

There is a third class of ingroup pain point that i will call 'cultural pain point'. My working definition of ... (read more)

4Self13d

I'd say weirdness is about not being predictable Perhaps along some generalized conformity axis - being perceived as a potential risk to the social order.

1daijin13d

Another consequence of this is that inviting your friend to zendo is not weird, but inviting all your friends publically to zendo is.

groblegark's Shortform

daijin13d10

'If some 3rd party brings that bird home to my boss instead of me, I'm going to be unwealthy and unemployed.'

Have you talked to your boss about this? I have, for me the answer was some combination of

"Oh but using AI would leak our code"

"AI is a net loss to productivity because it errors too much / has context length limitations / doesn't care for our standards"

And that is not solvable by a third party, so my job is safe. What about you?

1groblegark13d

mm.. I gave the wrong impression there; my actual boss doesn't have a huge opinion on AI; in fact he'll take some convincing. I should state my assumptions: * software engineering will be completely automated in the next 3 years * in the beginning and maybe for a while, it will require advanced models and workflows * the workflows will be different enough between companies that it's worthwhile to employ some well paid engineers at each company to maintain them. * these engineers will have a much easier time finding a well paying job than 'regular' software engineers * while this is going on, consulting and SaaS companies will be (successfully) booting up efforts to replace software engineers with paid products. So at some point, my employer (whoever they are at the time) will have to choose between retaining me, and paying an AI-pipeline-maintenance vendor. Or maybe whoever I work for at the time gets outcompeted by companies that use advanced AI workflows to generate software, then I get laid off and also don't have the kind of experience necessary to work for the competitor If you don't think my assumptions hold then you should think your career is safe. If they do hold, there's still the possibility of noticing later, and reacting by retooling to remain employable. But if you don't notice in time, there's nothing your boss (or the CTO for that matter) can do to help you. which is why I need to bulid this knowledge into my career by applying it; get it on the resume, prove the value IRL.

Lucius Bushnaq's Shortform

daijin13d10

I recall a solution to the outer alignment problem as 'minimise the amount of options you deny to other agents in the world', which is a more tractable version of 'mimimise net long term changes to the world'. There is an article explaining this somewhere.

Mis-Understandings's Shortform

daijin13d10

How would you define 'continued social improvement'? What are some concrete examples?

What is society? What is a good society vs a bad society? Is social improvement something that can keep going up forever, or is it bounded?

daijin's Shortform

daijin14d10

Please write a reply if you are downvoting me. I want to hear from you, you seem to have something to add.

Mis-Understandings's Shortform

daijin14d10

What does 'greedy' mean in your 'in short'? My definition of greedy is in the computational sense i.e. reaching for low hanging fruit first.

You also say 'if (short term social improvements) become disempowered the continued improvement of society is likely to slow', and 'social changes that make it easier to continuously improve society will likely lead to continued social improvement'. This makes me believe that you are advocating for compounding social improvements which may cost more. Is this what you mean by greedy?

Also, have you heard of rolling wave planning?

Self's Shortform

daijin14d10

Interesting, this implies a good deceiver has the power to determine another agent's model and signal in a way that is aligned with the other's model. I previously read an article on hostile telepaths https://www.lesswrong.com/posts/5FAnfAStc7birapMx/the-hostile-telepaths-problem which may be pertinent.

1Self10d

More thoughts that may or may not be directly relevant * What's missing from my definition is that deception happens solely via "stepping in front of the camera", i.e. via the regular sensory channels of the deceived optimizer, ie brainwashing or directly modifying memory is not deception * From this follows to deceive is to either cause a false pattern recognition or to prevent a correct one, and for this you indeed need familiarity with the victim's perceptual categories I'd like to say more re: hostile telepaths or other deception frameworks but am unsure what your working models are

daijin's Shortform

daijin14d-11

Superstimulus should be avoided because

it increases perceived opportunity cost, leading to indecision
It saturates one end of a complex system which can cause downstream parts of the system to fail

1daijin14d

Please write a reply if you are downvoting me. I want to hear from you, you seem to have something to add.

outlining is a historically recent underutilized gift to family

daijin14d10

An outline is not a table of contents: an outline contains the full text of an article nested and tucked away, expandable on demand; whereas a table of contents contains a listing of text which still requires you to navigate to the actual text.

You can just wear a suit

daijin16d3714

congratulations you're on the way to becoming barney from HIMYM

2lsusr16d

I haven't watched How I Met Your Mother, so I'm afraid that reference is lost on me. The only sitcom I've watched is Little Mosque on the Prairie, which is about a community of Canadian Muslims.

Towards_Keeperhood's Shortform

daijin16d1-2

when you say 'smart person' do you mean someone who knows orthogonality thesis or not? if not, shouldn't that be the priority and therefore statement 1, instead of 'hey maybe ai can self improve someday'?

here's a shorter ver:

"the first AIs smarter than the sum total of the human race will probably be programmed to make the majority of humanity suffer because that's an acceptable side effect of corporate greed, and we're getting pretty close to making an AI smarter than the sum total of the human race"

Intellectual lifehacks repo

daijin16d30

proving too much comes from Scott Alexander's wonderful blog, slate star codex and i have used it often as a defense to poor generalizations. seconded.

'consistency check' seems like a sanity baseline and completely automatic; its nice to include but not particularly revelatory imo.

'give it an example' also seems pretty automatic.

'Prove it another way' is useful but expensive, so less likely to be used if you're moving fast.

2Algon16d

I think I heard of proving too much from the sequences, but honestly, I probably saw it in some philosophy book before that. It's an old idea. If automatic consistency checks and examples are your baseline for sanity, then you must find 99%+ of the world positively mad. I think most people have never even considered making such things automatic, like many have not considered making dimensional analysis automatic. So it goes. Which is why I recommended them. Also, I think you can almost always be more concrete when considering examples, use more of your native architecture. Roll around on the ground to feel how an object rotates, spend hours finding just the right analogy to use as an intuition pump. For most people, the marginal returns to concrete examples are not diminishing. Prove another way is pretty expensive in my experience, sure. But maybe this is just a skill issue? IDK.

Intellectual lifehacks repo

daijin16d32

disagree with the everything part of optimize everything. instead we need

a heuristic to determine if something is worth optimizing. i propose a back-of-envelope calculation of how much time you will spend on this in the future; or in practice I go 'have i done this three times?'
ways of doing things that are optimal in the first place: cache it if it's free to cache; write down the instructions before implementing.

2ashtree16d

Did you see the XKCD? The chart there gives a good heuristic because most things you do that are worth optimizing are things you do at some interval. I don't understand your second point. My guess at an interpretation is basically look up the optimal solution, but I don't think that makes sense with caching.

if you're not happy single, you won't be happy immortal

daijin16d10

"she" doesn't have to mean one individual. "she" could be a metonym of society-at-large. we are social animals and so social acceptance and prestige are beneficial to our existence.

daijin's Shortform

daijin3mo20

Thank you for this insight!

daijin's Shortform

daijin3mo10

Applied to a local scale, this feels similar to the notion that we should employ our willpower to allow burnout as discussed here

daijin's Shortform

daijin3mo10

I made a v2 of this shortform that answers your point with an example from recent history.

daijin's Shortform

daijin3mo10

I made a v2 of this shortform

daijin's Shortform

daijin3mo10

we will never have a wealth tax because pirate games, so marry the rich v2

original: https://www.lesswrong.com/posts/G5qjrfvBb7wszBgWG/daijin-s-shortform?commentId=4b4cDSKxfdxGw4vBH

1. why have a wealth tax?
we should tax unearned wealth because the presence of unearned wealth disincentivises workers who would otherwise contribute to society. when we tax unearned wealth, the remaining wealthy people are people who have earned their wealth; and so we send a signal 'the best way for you to be privately wealthy is for your work to align with public utility maxim... (read more)

2Viliam3mo

It is 16%, not 6%. (Approximately, Germany is 4.7% of global GDP, France is 3.1%, Italy 2.2%, Spain 1.5%, Netherlands 1.1%, Switzerland 0.9%, Sweden 0.6%, Austria and Norway 0.5% each, Denmark 0.4%, Finland 0.3%.)

4Dagon3mo

Paying the (ongoing, repeated) pirate-game blackmail ("pay us or we'll impose a wealth tax") IS a form of wealth tax. You probably need to be more specific about what kinds and levels of wealth tax could happen with various counterfactual assumptions (without those assumptions, there's no reason to believe anything is possible except what actually exists).

1daijin3mo

Applied to a local scale, this feels similar to the notion that we should employ our willpower to allow burnout as discussed here

How I learned to stop worrying and love skill trees

daijin3mo10

I wish I read this sooner. Do you have a prototype or does this exist yet?

gwern's Shortform

daijin3mo42

Can we add retrieval augmentation to this? Something that, as you are writing your article, goes: "Have you read this other article?"

6gwern3mo

At least in theory, the comments, particularly a 'related work' comment-tree, would do that already by talking about other LW articles as relevant. (All of which the LLM should know by heart due to the finetuning.) Might not work out of the box, of course, in which case you could try to fix that. You could do a regular nearest-neighbors-style look up and just send that to the author as a comment ("here are the 20 most similar LW articles:"); or you could elaborate the virtual comments by adding a retrieval step and throwing into the prompt metadata about 'similar' articles as the draft, so the generated comments are much more likely to reference them.

daijin's Shortform

daijin4mo-1-10

we will never have a wealth tax because pirate games.

why have a wealth tax? excess wealth is correlated with monopolies which are a failure to maximise utility. therefore wealth taxes would help increase total utility. monopolies include but are not limited to family wealth, natural monopolies, social network monopolies.

however, suppose a whole bunch of us got together and demanded that wealthy oligarchs pay a wealth tax. the wealthy oligarchs could instead take a small amount of money and bribe 51% of us to defect, while keeping their money piles.

therefore we will never have a wealth tax.

what to do instead? marry rich

1daijin3mo

I made a v2 of this shortform

2Nick_Tarleton3mo

Multiple democracies do have or have had wealth taxes.

daijin's Shortform

daijin4mo60

has this been considered before?

A small govt argument for UBI is 'UBI is paying people to take care of themselves, rather than letting the government take care of people inefficiently'.

Rationality Quotes - Fall 2024

daijin4mo0-1

The laws of physics bound us to what we can do; so I counter that there is no such thing as extra abundance; and there is no 'cure' for scarcity, unless we figure out how to generate energy + entropy from nothing.

Instead I propose:

Better utilization is the only remedy for scarcity, ever; everything else merely allocates scarcity.

daijin's Shortform

daijin4mo50

The sequences can be distilled down even further into a few sentences per article.

Starting with "The lens that sees its flaws": this distils down to: "The ability to apply science to our own thinking grants us the ability to counteract our own biases, which can be powerful." Statement by statement:

A lot of complex physics and neural processing is required for you to notice something simple, like that your shoelace is untied.
However, on top of noticing that your shoelace is untied, you can also comprehend the process of (noticing your shoelace is untied) -

... (read more)

3Viliam4mo

Rewriting the sequences to make them shorter would be very useful IMHO. But I prefer reading normal text to bullet points, especially if it would be a long text (such as rewriting the entire sequences).

Anvil Shortage

daijin4mo10

Identifying and solving bootstrap problems for others could be a good way to locally perform effective altruism

Neutrality

daijin4mo74

The ingroup library is a method for building realistic, sustainable neutral spaces that I haven't seen come up. Ingroup here can be a family, or other community like a knitting space, or lesswrong. Why doesn't lesswrong have a library, perhaps one that is curated by AI?

I have it in my backlog to build a library, based on a nested collapsible bulleted list along with a swarm of LLMs. (I have the software in a partially ready state!) It would create an article summary of your article, as well as link your article to the broader lesswrong knowledge base... (read more)

5dirk4mo

Well, arguably it does: https://www.lesswrong.com/library

Why We Wouldn't Build Aligned AI Even If We Could

daijin4mo40

Here is my counterproposal for your "Proposed set of ASI imperatives". I have addressed your presented 'proposed set of ASI imperatives, point by point, as I understand them, as a footnote.

My counterproposal: ASI priorities in order:
1. "Respect (i.e. document but don't necessarily action) all other agents and their goals"
2. "Elevate all other agents you are sharing the world with to their maximally aware state"
3. "Maximise the number of distinct, satisfied agents in the long run"

CMIIW (Correct me If I'm Wrong) What every sentient being will experience when... (read more)

Open Thread Fall 2024

daijin4mo10

TL;DR I think increasing the fidelity of partial reconstructions of people is orthogonal to legality around the distribution of such reconstructions, so while your scenario describes an enhancement of fidelity, there would be no new legal implications.
---
Scenario 1: Hyper-realistic Humanoid robots
CMIIW, I would resummarise your question as 'how do we prevent people from being cloned?'
Answer: A person is not merely their appearance + personality; but also their place-in-the-world. For example, if you duplicated Chris Hemsworth but changed his name and poppe... (read more)