Bunthut

Replying toLack of Social Grace is a Lack of Skill

I was not, however, socially adroit, so what I said was “why do you care about something boring like horses?”
She complained to the teachers about me being rude, which in hindsight was entirely fair.

How normal would you rate the reaction? While you were being rude, I find it strange to complain to the teachers about just that. In my experience, not many people would do that past elementary school.

Replying toAre apples made of cells?

Bunthut3mo

Are apples made of cells?

I can't get spoiler tag to work so here it is

The seeds at least need to contain cells, because new plants with cells grow out of them. It's not a single cell because it's solid on the inside - I don't know any living cell that is, and it would be very difficult for substance transport. It also shows cell damage: a cut apple browns on the air, and the sharper the knife the less it does it. I don't think a case like bones can even be excluded without a microscope.

Replying toEnlightenment AMA

Bunthut5mo*

Enlightenment AMA

You mean discursive thinking like that voice in your head? Yeah, we do that in shikantaza. After you turn it off what's left is the sensation of the breath, the sound of wind chimes outside and, if your eyes are open, the image of the wall in front of you. It takes me about 30 minutes of deliberate intention in a peaceful room to get into this state.

I think getting rid of the voice in my head temporarily is very easy. Trivially, by replacing it with a loud repeating dum dum dum sound in my head, though Im not sure that counts. But I've also just done 30s of no auditory imagination while looking around in my non-blank room, and it took maybe 5s to get there. Is this one of those buddhist terms of art where it actually means way more than a layperson would reasonably think it does?

Replying toEnlightenment AMA

Bunthut5mo

Enlightenment AMA

According to predictive coding, believing you'll take an action just is how you take it, and believing you'll achieve a goal just is how you intend it. This would mean if you desire more than you can achieve, you experience prediction error, but if you desire less than you can achieve, you just underachieve with no psychological warning.

Replying toFutarchy's fundamental flaw

Bunthut8mo*

Futarchy's fundamental flaw

Suppose b is the true bias of the coin (which the supercomputer will compute). Then your expected return in this game is
𝔼[max(b, 0.50)] = 0.50 + 𝔼[max(b-0.50, 0)]

No. That formula would imply that, if the coin is 30% for sure and you buy it for 0.3, you make 0.2 in expectation, which you don't, you make 0 regardless of what price you buy at.

Note that this kind of problem has also shown up in decision theory more generally. This is a good place to start. In particular, it seems like your problem can be fixed with epsilon exploration (if it doesn't do so automatically, as per Soares), both the EDT and CDT variant should work.

Replying toIntelligence Is Not Magic, But Your Threshold For "Magic" Is Pretty Low

Bunthut8mo

Intelligence Is Not Magic, But Your Threshold For "Magic" Is Pretty Low

A simple version of this is done for panoramic photos. If he looked at the city from a consistent direction throughout the flight, that's all that's needed. If the direction varied, it can't have varied a lot - he had to at least see the sides of the building he was drawing, if maybe from a different angle, and not all the buildings would have been parallel. That kind of rotation seems doable with current image transformers (and that's only neccesary if the drawing has accurate angles even over long distances).

In any case, I don't think it matters to my argument if current ML can do it. All the parts that might be difficult for the computer are doable even for normal humans, and therefore not magical. The only thing that's added to the normal human skill here is perfect memory, which we know is easy for computers and have known for a long time.

Replying toAre superhuman savants real?

Bunthut8mo

Are superhuman savants real?

To clarify the question: I agree that there is variation in talent and that some very talented people can do things most could never. My question is, if you look at the distribution of talent among normal people, and then check how many standard deviations out our savant candidate is, then what's the chance at least one person with that talent would exist? Basically, is this just the normal right tail that's expected from additive genetic reshuffling, or an "X-man".

Are superhuman savants real?

Bunthut

8mo

Savant syndrom indentifies people with general intellectual impairment who, in one specific field, reach ordinary or even exceptional performance.

In The Psychological Unity of Humankind, Eliezer argues that

So you can't have the X-Men. You can't have "mutants" running around with highly developed machinery that most of the human species doesn't have. And no, extra-powerful radiation does not produce extra-potent mutations, that's not how it works.
Again by the nature of sexual recombination, you're very unlikely to see two complexly different adaptations competing in the gene pool. Two individual alleles may compete. But if you somehow had two different complex adaptations built out of many non-universal alleles, they would usually assemble in scrambled form.

The argument... (read 152 more words →)

Replying toIntelligence Is Not Magic, But Your Threshold For "Magic" Is Pretty Low

Bunthut8mo

Intelligence Is Not Magic, But Your Threshold For "Magic" Is Pretty Low

Example 3: Stephen Wiltshire. He made a nineteen-foot-long drawing of New York City after flying on a helicopter for 20 minutes, and he got the number of windows and floors of all the buildings correct.

I think ~everyone understands that computers can do this. The "magical" part is doing it with a human brain, not doing it at all. Similarly, blindfolded chess is not more difficult than normal chess for computers. That may take a little knowledge to see. And "doing it faster" is again clear. So the threshold for magic you describe is not the one even the most naive use for AI.

-1

Replying toWhy Have Sentence Lengths Decreased?

Bunthut10mo*

Why Have Sentence Lengths Decreased?

Sentence lengths have declined.

Data: I looked for similar data on sentence lengths in german, and the first result I found covering a similar timeframe was wikipedia referencing Kurt Möslein: Einige Entwicklungstendenzen in der Syntax der wissenschaftlich-technischen Literatur seit dem Ende des 18. Jahrhunderts. (1974), which does not find the same trend:

Year	wps
1770	24,50
1800	25,54
1850	32,00
1900	23,58
1920	22,72
1940	19,60
1960	19,90

This data on scientific writing starts lower than any of your english examples from that time, and increases initially, but arrives in the same place (insofar as wps are comparably across languages, which I think is fine for english and german).

Replying toLessWrong has been acquired by EA

Bunthut10mo

LessWrong has been acquired by EA

6 picolightcones as well, don't think that changed.

Identifiability Problem for Superrational Decision Theories

Bunthut

Superrationality, and generalizations of it, must treat options differently depending on how they're named.

Consider the penny correlation game: Both players decide independently on either head or tails. Then if they decided on the same thing, they each get one util, otherwise they get nothing. You play this game with an exact copy of yourself. You reason: since the other guy is an exact copy of me, whatever I do he will do the same thing. So we will get the util. Then you pick heads because its first alphabetically or some other silly consideration, and then you win. How good that you got to play with a copy, otherwise you would have... (read 335 more words →)

Phylactery Decision Theory

Bunthut

This is definitely a hack, but it seems to solve many problems around Cartesian Boundaries. Much of this is development of earlier ideas about the Predict-O-Matic, see there if something is unclear.

Phylactery Decision Theory takes a Base Decision Theory (BDT) as an input and builds something around it, creating a new modified decision theory. Its purpose it to give its base the ability to """learn""" its position in the world.

I'll start by explaining a model of it in a Cartesian context. Lets say we have an agent, with a set of designated input and output channels. Then it makes its "decisions" like this: First, it has a probability distribution over everything, including... (read 575 more words →)

Learning Russian Roulette

Bunthut

Surprisingly, our current theories of anthropics don't seem to cover this.

You have a revolver with six chambers. One of them has a bullet in it. You are offered $1 for spinning the barrel, pointing at your head, and pulling the trigger. You remember doing this many times, and surviving each time. You also remember many other people doing this many times, and dying about 1/6th of the time. Should you play another round?

It seems to me that the answer is no, but existing formal theories disagree. Consider two hypothesis: A says that everyone has a 1/6 chance of dying. B says that everyone else has a 1/6 chance of dying, but I... (read 550 more words →)

Fisherian Runaway as a decision-theoretic problem

Bunthut

Introducing what I think may be an interesting toy problem for timeless-like considerations.

The Fisherian Runaway is a proposed mechanism for the development of apparently-detrimental ornamentation such as peacock tails. It goes something like this: You start out with females being selective about their mates. They develop some form of evaluation system to select for fitness in their mates. Then, a male with some new trait comes along. For whatever reason, the existing fitness-evaluation system rates this trait very highly. The male finds many mates and has many offspring. His sons will also carry the new trait, and will similarly have more offspring than replacement. The trait will spread through the population. Then,... (read 793 more words →)

A non-logarithmic argument for Kelly

Bunthut

This post is a response to abramdemski's post, Kelly *is* (just) about logarithmic utility.

any argument in favor of the Kelly formula has to go through an implication that your utility is logarithmic in money, at some point. If it seems not to, it's either:
mistaken
cleverly hiding the implication
some mind-blowing argument I haven't seen before.

Challenge accepted. This is essentially a version of time-averageing which gets rid of the infinity-problem.

Consider the Kelly-betting game: Each round, you can bet any fraction of your wealth on a fair coinflip, which will be tripled if you win. You play this game for an infinite number of rounds. Your utility is linear in money.

The first thing to note is... (read 456 more words →)

Learning Normativity: Language

Bunthut

Abram Demski has been writing about Normativity. The suggested models so far have mostly looked at actions rather than semantics, despite suggestions that this is possible and language learning as a motivating example. There is a simple mechanism that seems to me to mostly fit that bill.

Model

There is an interpreter and an assumed speaker. The interpreter receives observation data as an input, which contains some things put there by the speaker among others. The interpreter has a language in which it can express all its beliefs. Since we want to form beliefs about meaning, this language can talk about meaning: it can from propositions of the form "[Observation] means [propositon].". Note that... (read 2389 more words →)

Limiting Causality by Complexity Class

Bunthut

The standard account of causality depends on the idea of intervention: The question of what follows if X not just naturally occurs, but we bring it about artificially independently of its usual causes. This doesn't go well with embedded agency. If the agent is part of the world, then its own actions will always be caused by the past state of the world, and so it couldnt know if the apparent effect of its interventions isn't just due to some common cause. There is a potential way out of this if we limit the complexity of causal dependencies.

Classically, X is dependent on Y iff the conditional distribution of X on Y is... (read 253 more words →)

What is the interpretation of the do() operator?

Bunthut

To reductively explain causality, it has to be explained in non-causal terms, most likely in terms of total propability distributions. Pearl explains causality in terms of causal graphs which are created by conditionalizing the propability distribution on not $e v e n t$ , but $d o (e v e n t)$ . What does this mean? It's easy enough to explain in causal terms: You make it so $e v e n t$ occurs without changing any of its causal antecedents. But of course that fails to explain causality. How could it be explained without that?

Towards a Formalisation of Logical Counterfactuals

Bunthut

Introduction

This is an attempt to build a basis for formalising logical counterfactuals. It's not workable as is, but I think it can potentially solve the problem of "outthinking the counterfactual".

For causal counterfactuals, we build a directed acyclic causal graph. We then modify the value of the node representing the condition, and recompute the value of the descendent nodes. I try to mirror this apporach.

The nodes of our new graph will of course be propositions, and the edges inferences. There are problems however. An inference can have multiple antecedents, and we cant just represent this by giving them all and edge to the consequent, because there can also be multiple ways to infer... (read 556 more words →)

LESSWRONG
LW

LESSWRONG
LW

Learning Russian Roulette

A non-logarithmic argument for Kelly

Limiting Causality by Complexity Class

Identifiability Problem for Superrational Decision Theories

Bunthut

Bunthut

Are superhuman savants real?

Identifiability Problem for Superrational Decision Theories

Phylactery Decision Theory

Learning Russian Roulette

Fisherian Runaway as a decision-theoretic problem

A non-logarithmic argument for Kelly

Learning Normativity: Language

Bunthut

Learning Russian Roulette

A non-logarithmic argument for Kelly

Limiting Causality by Complexity Class

Identifiability Problem for Superrational Decision Theories

Bunthut

Bunthut

Are superhuman savants real?

Identifiability Problem for Superrational Decision Theories

Phylactery Decision Theory

Learning Russian Roulette

Fisherian Runaway as a decision-theoretic problem

A non-logarithmic argument for Kelly

Learning Normativity: Language

Model