All of Purged Deviator's Comments + Replies

"he sounds convincing when he talks about X."

I am so disappointed every time I see people using the persuasiveness filter. Persuasiveness is not completely orthogonal to correctness, but it is definitely linearly independent from it.

You discuss "compromised agents" of the FBI as if they're going to be lone, investigator-level agents.  If there was going to be any FBI/CIA/whatever cover-up, the version of that which I would expect, is that Epstein would've had incriminating information on senior FBI/CIA personnel, or politicians.  Incriminating information could just be that the FBI/CIA knew that Epstein was raping underage girls for 20 years, and didn't stop him, or even protected him.  In all your explanations of how impossible a crime Epstein's murder would be to pull... (read more)

Now that I've had 5 months to let this idea stew, when I read your comment again just now, I think I understand it completely?  After getting comfortable using "demons" to refer to patterns of thought or behavior which proliferate in ways not completely unlike some patterns of matter, this comment now makes a lot more sense than it used to.

2MSRayne
Lovely! I'm glad to hear it's making sense to you. I had a leg up in perceiving this - I spent several years of my youth as a paranoid, possibly schizotypal occultist who literally believed in spirits - so it wasn't hard for me, once I became more rational, to notice that I'd not been entirely wrong. But most people have no basis from which to start when perceiving these things!
  1. Yeah.  I wanted to assume they were being forced to give an opinion, so that "what topics a person is or isn't likely to bring up" wasn't a confounding variable.  Your point here suggests that a conspirator's response might be more like "I don't think about them", or some kind of null opinion.
  2. This sort of gets to the core of what I was wondering about, but am not sure how to solve: how lies will tend to pervert Bayesian inference.  "Simulacra levels" may be relevant here.  I would think that a highly competent conspirator would want to
... (read more)

without using "will"

Oh come on.  Alright, but if your answer mentions future or past states, or references time at all, I'm dinging you points.  Imaginary points, not karma points obviously.

So let's talk about this word, "could".  Can you play Rationalist's Taboo against it? 

Testing myself before I read further.  World states which "could" happen are the set of world states which are not ruled impossible by our limited knowledge.  Is "impossible" still too load-bearing here?  Fine, let's get more concrete.

In a finite-size game of Conway's Life, each board state has exactly one following board state, which itself has only one following board state, and so on.  This sequence of board states is a board's future. &nb... (read more)

-1Purged Deviator
Oh come on.  Alright, but if your answer mentions future or past states, or references time at all, I'm dinging you points.  Imaginary points, not karma points obviously.

So then this initial probability estimate, 0.5, is not repeat not a "prior".

1:1 odds seems like it would be a default null prior, especially because one round of Bayes' Rule updates it immediately to whatever your first likelihood ratio is, kind of like the other mathematical identities.  If your priors represent "all the information you already know", then it seems like you (or someone) must have gotten there through a series of Bayesian inferences, but that series would have to start somewhere, right?   If (in the real universe, not the ball &a... (read more)

Evil is a pattern of of behavior exhibited by agents.  In embedded agents, that pattern is absolutely represented by material.  As for what that pattern is, evil agents harm others for their own gain.  That seems to be the core of "evilness" in possibility space.  Whenever I try to think of the most evil actions I can, they tend to correlate with harming others (especially one's equals, or one's inner circle, who would expect mutual cooperation), for one's own gain.  Hamlet's uncle.  Domestic abusers.  Executives who ruin... (read more)

Not really.  "Collapse" is not the only failure case.  Mass starvation is a clear failure state of a planned economy, but it doesn't necessarily burn through the nation's stock of proletariat laborers immediately.  In the same way that a person with a terminal illness can take a long time to die, a nation with failing systems can take a long time to reach the point where it ceases functioning at all.

How do lies affect Bayesian Inference?

(Relative likelihood notation is easier, so we will use that)

I heard a thing.  Well, I more heard a thing about another thing.  Before I heard about it, I didn't know one way or the other at all.  My prior was the Bayesian null prior of 1:1.  Let's say the thing I heard is "Conspiracy thinking is bad for my epistemology".  Let's pretend it was relevant at the time, and didn't just come up out of nowhere.  What is the chance that someone would hold this opinion, given that they are not part... (read more)

3JBlack
There are lots of holes. Here are a few: 1. If they're actually in a conspiracy against you, it's likely that they don't even want you thinking about conspiracies. It's not in their interest for you to associate them with the concept "conspiracy" in any way, since people who don't think about conspiracies at all are unlikely to unmask them. By this reasoning, the chance of a conspirator drawing attention to thinking about conspiracies is not anywhere near 95% - maybe not even 20%. 2. A highly competent conspiracy member will give you no information that distinguishes the existence of the conspiracy from the non-existence of the conspiracy. If you believe that they have voluntarily given you such information, then you should rule out that the conspiracy consists of competent members. This takes a chunk out of your "this person is a conspirator" weight. 3. There are always more hypotheses. Splitting into just two and treating them as internally homogeneous is always a mistake. I hope this helps! Thinking about conspiracies doesn't have to be bad for your epistemology, but I suspect that in practice it is much more often harmful than helpful.
3Measure
The event is more likely to occur if the person is a conspirator, so you hearing the statement should indeed increase your credence for conspiracy (and symmetrically decrease your credence for not-conspiracy).

weight-loss-that-is-definitely-not-changes-in-water-retention comes in chunks

Source for my answer: for the last 10 months, I have fasted regularly, with various fasts from 16 hours to 7 days, with & without vitamins, including water fasts, electrolyte fasts, and dry fasts. During this time, I have weighed myself multiple times per day. [I have lost >100 lbs doing this, but that's not important right now.]

How hydrated you are at any given time is a confounding variable whenever you weigh yourself. My body can hold plus or minus nearly a gallon o... (read more)

Started reading, want to get initial thoughts down before they escape me. Will return when I am done

Representation: An agent, or an agent's behaviour, is a script. I don't know if that's helpful or meaningful. Interfaces: Real, in-universe agents have hardware on which they operate. I'd say they have "sensors and actuators", but that's tautologous to "inputs and outputs". Embedding: In biological systems, the script is encoded directly in the structure of the wetware. The hardware / software dichotomy has more separation, but I think I'm probably misunderstanding this.

Monopolies on the Use of Force

[Epistemic status & effort: exploring a question over an hour or so, and constrained to only use information I already know. This is a problem solving exercise, not a research paper. Originally written just for me; minor clarification added later.]

Is the use of force a unique industry, where a single monolithic [business] entity is the most stable state, the equilibrium point? From a business perspective, an entity selling the use of force might be thought of as in a "risk management" or "contract enforcement" industry.... (read more)

4Dagon
This is a good topic for investigation, but you probably need to model it in more detail than you currently are.  There are many dimensions and aspects to use of violence (and the threat of violence) that don't quite fit the "monopoly" model.  And many kinds of force/coercion that aren't directly violent, even if they're tenuously chained to violence via many causal steps.   I very much like the recognition that it's an equilibrium - there are multiple opposing (and semi-opposing, if viewed in multiple dimensions) actors with various strength and willingness to harm or cooperate.  It's not clear whether there's a single solution at any given time, but it is clear that it will shift over time, sometimes quickly, often slowly. Another good exploration is "what rights exist without being enforced by violence (or the distant threat of violence)?"  I'd argue almost none.  

Nope.  Nopenopenope.  This trips so many cult flags.  This does not feel like rationality, this feels like pseudoreligion, like cult entrance activities, with rationality window dressing.

 

Maybe it's just because of the "you have to experience it for yourself" theme of this article, but right now this gets a hard nope from me, like psychedelics & speaking in tongues.

 

Nope.

I don't expect AI researchers to achieve AGI before they find one or more horrible uses for non-general AI tools, which may divert resources, or change priorities, or do something else which prevents true AGI from ever being developed.

That's what I use this place for, an audience for rough drafts or mere buddings of an idea.  (Crippling) Executive dysfunction sounds like it may be a primary thing to explore & figure out, but it also sounds like the sort of thing that surrounds itself with an Ugh Field very quickly.  Good luck!

2DragonGod
I can persevere in the timescale of hours to a few days. I cannot dedicate myself on the timescale of weeks let alone months or years.
3MSRayne
You might want to look into the chaos magick notion of "egregores". Particularly the less woo bits based on meme theory and cybernetics. Essentially: it is reasonable to suspect that there are human mind subagents capable of replicating themselves across people by being communicated, and cooperating with their copies in other hosts to form larger, slower collective minds. To me it seems like such "egregores" include deities, spirits, corporations, nations, and all other agenty social constructs. It is in fact exactly correct that people can and do, regularly, get possessed by spirits. Think of your favorite annoying identity politics group and how they all look and act roughly the same, and make irrational decisions that benefit the desire of their identity group to spread itself to new humans more than their own personal well being. Social media has enabled these entities to spread their influence far faster than ever before, and they are basically unaligned AIs running on human wetware, just itching to get themselves uploaded - a lesser-appreciated possible failure mode of AGI in my opinion.

When Grothendieck was learning math, he was playing Dark Souls.

I think you may have waded into the trees here, before taking stock of the forest.  By which I mean that this problem could definitely use some formalization, and may be much more important than we expect it to be.  I've been studying the ancient Mongols recently; their conquests tested this, and their empire had the potential to be a locked-in dystopia type of apocalypse, but they failed to create a stable internal organizational structure.  Thus, a culture that optimizes for both conquest & control, at the expense of everything else, c... (read more)

Whom/what an agent is willing to do Evil to, vs whom/what it would prefer to do Good to, sort of defines an in-group/out-group divide, in a similar way to how the decision to cooperate or defect does in the Prisoner's Dilemma.  Hmmm...

you enjoy peacefully reading a book by yourself, and other people hate this because they hate you and they hate it when you enjoy yourself

The problem with making hypothetical examples, is when you make them so unreal as to just be moving words around.  Playing music/sound/whatever loud enough to be noise pollution would be similar to the first example.  Less severe, but similar.  Spreading manure on your lawn so that your entire neighborhood stinks would also be less severe, but similar.  But if you're going to say "reading" and then ha... (read more)

1localdeity
Ok, if you want more realistic examples, consider: * driving around in a fancy car that you legitimately earned the money to buy, and your neighbors are jealous and hate seeing it (and it's not an eyesore, nor is their complaint about wear and tear on the road or congestion) * succeeding at a career (through skill and hard work) that your neighbors failed at, which reminds them of their failure and they feel regret * marrying someone of a race or sex that causes some of your neighbors great anguish due to their beliefs * maintaining a social relationship with someone who has opinions your neighbors really hate * having resources that they really want—I mean really really want, I mean need—no matter how much you like having it, I can always work myself up into a height of emotion such that I want it more than you, and therefore aggregate utility is optimized if you give it to me The category is "peaceful things you should be allowed to do—that I would write off any ethical system that forbade you from doing—even though they (a) benefit you, (b) harm others, and (c) might even be net-negative (at least naively, in the short term) in aggregate utility".  The point is that other people's psyches can work in arbitrary ways that assign negative payoffs to peaceful, benign actions of yours, and if the ethical system allows them to use this to control your behavior or grab your resources, then they're incentivized to bend their psyches in that direction—to dwell on their envy and hatred and let them grow.  (Also, since mind-reading isn't currently practical, any implementation of the ethical system relies on people's ability to self-report their preferences, and to be convincing about it.)  The winners would be those who are best able to convince others of how needy they are (possibly by becoming that needy). Therefore, any acceptable ethical system must be resistant to this kind of utilitarian coercion.  As I say, rules—generally systems of rights, generally those

The first paragraph is equivalent to saying that "all good & evil is socially constructed because we live in a society", and I don't want to call someone wrong, so let me try to explain...

An accurate model of Good & Evil will hold true, valid, and meaningful among any population of agents: human, animal, artificial, or otherwise. It is not at all depentent on existing in our current, modern society. Populations that do significant amounts of Good amongst each other generally thrive & are resilient (e.g. humans, ants, rats, wolves, cells in an... (read more)

-2Dagon
I look forward to seeing such a model.  Or even the foundation of such a model and an indication of how you know it's truly about good and evil, rather than efficient and in-.  

For self-defense, that's still a feature, and not a bug. It's generally seen as more evil to do more harm when defending yourself, and in law, defending youself with lethal force is "justifyable homicide", it's specifically called out as something much like an "acceptable evil". Would it be more or less evil to cause an attacker to change their ways without harming them? Would it be more or less evil to torture an attacker before killing them?

"...by not doing all the Good..." In the model, it's actually really intentional that "a lack of Good" is not a ... (read more)

I do agree for the most part. Robotic warfare which can efficiently destroy your opponent's materiel, without directly risking your own materiel & personnel is an extremely dominant strategy, and will probably become the future of warfare. At least warfare like this, as opposed to police actions.

I kinda wonder if this is what happened with Eliezer Yudkowsky, especially after he wrote Harry Potter and the Methods of Rationality?

From things I have previously heard about drones, I would be uncertain what training is required to operate them, and what limitations there are for weather in which they can & cannot fly.  I know that being unable to fly in anything other than near-perfect weather conditions has been a problem of drones in the past, and those same limitations do not apply to ground-based vehicles.  

2Daniel Kokotajlo
This is a good point, but it doesn't change the bottom line I think. Weather is more often good than bad, so within a few days of the war beginning there should be a chance for 1000 drones to rise and sweep the field. As for training, in the scenario where they bought 1000 drones they'd also do the necessary training for 1000 drone operators (though there are returns to scale I think; in a pinch 1 operator could probably handle 10 drones, just have them all flock in loose formation and then it's as if you have 1 big drone with 10x the ammunition capacity.)

Here's an analysis by Dr. Robert Malone about the Ukraine biolabs, which I found enlightening:

https://rwmalonemd.substack.com/p/ukraine-biolab-watchtower?r=ta0o1&s=w&utm_campaign=post&utm_medium=web

I glean that "biolab" is actually an extremely vague term, and doesn't specify the facility's exact capabilities at all.  They could very well have had an innocuous purpose, but Russia would've had to treat them as a potential threat to national security, in the same way that Russian or Chinese "biolabs" in Mexico might sound bad to the US, except Russia is even more paranoid.

The Definition of Good and Evil

Epistemic Status: I feel like I stumbled over this; it has passed a few filters for correctness; I have not rigorously explored it, and I cannot adequately defend it, but I think that is more my own failing than the failure of the idea.

I have heard said that "Good and Evil are Social Constructs", or "Who's really to say?", or "Morality is relative".  I do not like those at all, and I think they are completely wrong.  Since then, I either found, developed, or came across (I don't remember how I got this) a model of G... (read more)

-1Purged Deviator
Whom/what an agent is willing to do Evil to, vs whom/what it would prefer to do Good to, sort of defines an in-group/out-group divide, in a similar way to how the decision to cooperate or defect does in the Prisoner's Dilemma.  Hmmm...
0localdeity
I think, to form an ethical system that passes basic muster, you can't only take into account the immediate good/bad effects on people of an action.  That would treat the two cases "you dump toxic waste on other people's lawns because you find it funny" and "you enjoy peacefully reading a book by yourself, and other people hate this because they hate you and they hate it when you enjoy yourself" the same. If you start from a utilitarian perspective, I think you quickly figure out that there need to be rules—that having rules (which people treat as ends in themselves) leads to higher utility than following naive calculations.  And I think some version of property rights is the only plausible rule set that anyone has come up with, or at least is the starting point.  Then actions may be considered ethically bad to the extent that they violate the rules. Regarding Good and Evil... I think I would use those words to refer to when someone is conscious of the choice between good and bad actions, and chooses one or the other, respectively.  When I think of "monstrously evil", I think of an intelligent person who understands good people and the system they're in, and uses their intelligence and their resources to e.g. select the best people and hurt them specifically, or to find the weakest spots and sabotage the system most thoroughly and efficiently.  I can imagine a dumb evil person, but I think they still have to know that an option is morally bad and choose it; if they don't understand what they're doing in that respect, then they're not evil.
3Richard_Kennaway
That makes self-defence Evil. It even makes cultivating one's own garden Evil (by not doing all the Good that one might). And some argue that. Do you?
2Dagon
Your intuitions about what's good and what's evil are fully consistent with morality being relative, and with them being social constructs.  You are deeply embedded in many overlapping cultures and groups, and your beliefs about good and evil will naturally align with what they want you to believe (which in many cases is what they actually believe, but there's a LOT of hypocrisy on this topic, so it's not perfectly clear). I personally like those guidelines.  Though I'd call it good to help others EVEN if you benefit in doing so, and evil to do significant net harm, but with a pretty big carveout for small harms which can be modeled as benefits on different dimensions.  And my liking them doesn't make them real or objective.  

With priors of 1 or 0, Bayes rule stops working permanently.  If something is running on real hardware, then it has a limit on its numeric precision.  On a system that was never designed to make precise mathematical calculations, one where 8/10 doesn't feel significantly different from 9/10, or one where "90% chance" feels like "basically guaranteed", the level of numeric precision may be exceedingly low, such that it doesn't even take a lot for a level of certainty to be either rounded up to one or rounded down to 0.

As always, thanks for the post!

Well, it has helped me understand & overcome some of the specific ways that akrasia affects me, and it has also helped me understand how my own mind works, so I can alter and (hopefully) optimize it.

What do you disagree about?

I don't know.  Possibly something, probably nothing.

the essence of [addition as addition itself]... 

The "essence of cognition" isn't really available for us to study directly (so far as I know), except as a part of more complex processes.   Finding many varied examples may help determine what is the "essence" versus what is just extraneous detail.

While intelligent agency in humans is definitely more interesting than in amoebas, knowing exactly why amoebas aren't intelligent agents would tell you one detail about wh... (read more)

2TekhneMakre
Exactly, yeah; I think in the particular case of amoebas the benefit looks more like this, and it doesn't so much look like amoebas positively exemplifying much that's key about the kind of agency we're interested in re/ alignment. Which is why I disagree with the OP.

I didn't pick it up from any reputable sources.  The white paper on military theory that created the term was written many years ago, and since then I've only seen that explanation tossed around informally in various places, not investigated with serious rigor.  OODA loops seem to be seldom discussed on this site, which I find kinda weird, but a good full explanation of them can be found here: Training Regime Day 20: OODA Loop 

I tried to figure out on my own whether executing an OODA loop was necessary & sufficient condition for somethin... (read more)

4Daniel Kokotajlo
I asked because that's a reasonable one-line approximation of my own tentative theory of agency. I'm happy to hear that other people have similar intuitions! Alas that there isn't a fleshed out paper I can go read. Do you have any... nonreputable sources to link me to, that I might benefit from reading?

An explanation that I've seen before of "where agency begins" is when an entity executes OODA loops. I don't know if OODA loops are a completely accurate map to reality, but they've been a useful model so far. If someone were going to explore "where agency begins" OODA loops might be a good starting point.

I feel like an article about "what agency is" must've already been written here, but I don't remember it. In any case, that article on agency in Conway's Life sounds like my next stop, thank you for linking it!

3lc
Useful model so far meaning what?
3Daniel Kokotajlo
Where did you see that explanation? I want to go read it!

"You can't understand digital addition without understanding Mesopotamian clay token accounting"

That's sort of exactly correct? If you fully understand digital addition, then there's going to be something at the core of clay token accounting that you already understand. Complex systems tend to be built on the same concepts as simpler systems that do the same thing. If you fully understand an elevator, then there's no way that ropes & pulleys can still be a mystery to you, right? And to my knowledge, studying ropes & pulleys is a step in how we ... (read more)

3TekhneMakre
What do you disagree about? I agree that understanding addition implies that you understand something important about token accounting. I think there's something about addition that is maybe best learned by studying token accounting or similar (understanding how minds come to practice addition). I also think much of the essence of [addition as addition itself] is best and most easily understood in a more normal way--practicing counting and computing things in everyday life--and *not* by studying anything specifically about Mesopotamian clay token accounting, because relative to much of the essence of addition, historical accounting systems are baroque with irrelevant detail, and are a precursor or proto form of practicing addition, hence don't manifest the essence of addition in a refined and clear way. I like your elevator example. I think it's an open question whether / how amoebas are manifesting the same principles as (human, say) agency / mind / intelligence, i.e. to what extent amoebas are simpler models of the same thing (agent etc.) vs. models of something else (such as deficient agency, a subset of agency, etc.). I mean, my point isn't that there's some "amount" that amoebas "are agents" or whatever, that's not exactly well-defined or interesting, my point is that the reasons we're interested in agency make human agency much more interesting than amoeba agency, and this is not primarily a mistake; amoebas pretty much just don't do fictive learning, logical inference, etc., even though if you try you can read into amoebas a sort of deficient/restricted form of these things.

I've wondered this a lot too. There is a lot of focus on and discussion about "superintelligent" AGI here, or even human-level AGI, but I wonder what about "stupid" AGI? When superintelligent AGI is still out of reach, is there not something still to be learned from a hypothetical AGI with the intelligence level of, say, a crow?

3Shmi
Right, something like that. A crow is smart though. That's why I went picked an example of a single-cell organism.

[comment removed by author]

2Richard_Kennaway
Yes: this page contains a link to his solution.

Archaeologist here, I'll be taking this comment as permission!

Okay, this may be one of the most important articles I've read here.  I already knew about OODA loops and how important they are, but putting names to the different failure modes, which I have seen and experienced thousands of times, gives me the handles with which to grapple them.  

The main thing I want to say is thank you, I'm glad I didn't have to write something like this myself, because I do not know if it would have been nearly as clear & concise or nearly as good!

That Monte Carlo Method sounds a lot like dreaming.

Oof, be wary of Tim Ferriss, for he is a giant phony.  I bought one of his books once, and nearly every single piece of advice in it was a bad generalization from a single study, and all of it was either already well known outside of the book, or ineffective, or just plain wrong.  I have had great luck by immediately downgrading the trustworthiness of anything that mentions him, and especially anything that treats him as an authority.  I have found the same with NLP.  Please don't join that club.

Tim Ferriss is an utterly amoral agent. &... (read more)