Posts

Introduction To The Infra-Bayesianism Sequence 2020-08-27T08:02:54.872Z · score: 78 (27 votes)
Basic Inframeasure Theory 2020-08-27T08:02:06.109Z · score: 15 (5 votes)
Belief Functions And Decision Theory 2020-08-27T08:00:51.665Z · score: 7 (4 votes)
Proofs Section 1.1 (Initial results to LF-duality) 2020-08-27T07:59:12.512Z · score: 6 (3 votes)
Proofs Section 1.2 (Mixtures, Updates, Pushforwards) 2020-08-27T07:57:27.622Z · score: 7 (2 votes)
Proofs Section 2.1 (Theorem 1, Lemmas) 2020-08-27T07:54:59.744Z · score: 7 (2 votes)
Proofs Section 2.2 (Isomorphism to Expectations) 2020-08-27T07:52:08.121Z · score: 7 (2 votes)
Proofs Section 2.3 (Updates, Decision Theory) 2020-08-27T07:49:05.047Z · score: 7 (2 votes)
Counterfactual Induction (Lemma 4) 2019-12-17T05:05:15.959Z · score: 4 (1 votes)
Counterfactual Induction (Algorithm Sketch, Fixpoint proof) 2019-12-17T05:04:25.054Z · score: 5 (1 votes)
Counterfactual Induction 2019-12-17T05:03:32.401Z · score: 23 (5 votes)
CO2 Stripper Postmortem Thoughts 2019-11-30T21:20:33.685Z · score: 121 (37 votes)
A Brief Intro to Domain Theory 2019-11-21T03:24:13.416Z · score: 19 (10 votes)
So You Want to Colonize The Universe Part 5: The Actual Design 2019-02-27T10:23:28.424Z · score: 17 (11 votes)
So You Want to Colonize The Universe Part 4: Velocity Changes and Energy 2019-02-27T10:22:46.371Z · score: 13 (8 votes)
So You Want To Colonize The Universe Part 3: Dust 2019-02-27T10:20:14.780Z · score: 17 (10 votes)
So You Want to Colonize the Universe Part 2: Deep Time Engineering 2019-02-27T10:18:18.209Z · score: 13 (8 votes)
So You Want to Colonize The Universe 2019-02-27T10:17:50.427Z · score: 16 (15 votes)
Failures of UDT-AIXI, Part 1: Improper Randomizing 2019-01-06T03:53:03.563Z · score: 15 (6 votes)
COEDT Equilibria in Games 2018-12-06T18:00:08.442Z · score: 15 (4 votes)
Oracle Induction Proofs 2018-11-28T08:12:38.306Z · score: 6 (2 votes)
Bounded Oracle Induction 2018-11-28T08:11:28.183Z · score: 30 (11 votes)
What are Universal Inductors, Again? 2018-11-07T22:32:57.364Z · score: 11 (5 votes)
When EDT=CDT, ADT Does Well 2018-10-25T05:03:40.366Z · score: 14 (4 votes)
Asymptotic Decision Theory (Improved Writeup) 2018-09-27T05:17:03.222Z · score: 29 (8 votes)
Reflective AIXI and Anthropics 2018-09-24T02:15:18.108Z · score: 19 (8 votes)
Cooperative Oracles 2018-09-01T08:05:55.899Z · score: 19 (11 votes)
VOI is Only Nonnegative When Information is Uncorrelated With Future Action 2018-08-31T05:13:11.916Z · score: 23 (10 votes)
Probabilistic Tiling (Preliminary Attempt) 2018-08-07T01:14:15.558Z · score: 15 (9 votes)
Conditioning, Counterfactuals, Exploration, and Gears 2018-07-10T22:11:52.473Z · score: 30 (6 votes)
Logical Inductor Tiling and Why it's Hard 2018-06-14T06:34:36.000Z · score: 2 (2 votes)
A Loophole for Self-Applicative Soundness 2018-06-11T07:57:26.000Z · score: 1 (1 votes)
Resource-Limited Reflective Oracles 2018-06-06T02:50:42.000Z · score: 4 (3 votes)
Logical Inductors Converge to Correlated Equilibria (Kinda) 2018-05-30T20:23:54.000Z · score: 2 (2 votes)
Logical Inductor Lemmas 2018-05-26T17:43:52.000Z · score: 0 (0 votes)
Two Notions of Best Response 2018-05-26T17:14:19.000Z · score: 0 (0 votes)
Doubts about Updatelessness 2018-05-03T05:44:12.000Z · score: 1 (1 votes)
Program Search and Incomplete Understanding 2018-04-29T04:32:22.125Z · score: 42 (14 votes)
No Constant Distribution Can be a Logical Inductor 2018-04-07T09:09:49.000Z · score: 13 (6 votes)
Musings on Exploration 2018-04-03T02:15:17.000Z · score: 1 (1 votes)
A Difficulty With Density-Zero Exploration 2018-03-27T01:03:03.000Z · score: 0 (0 votes)
Distributed Cooperation 2018-03-18T05:46:56.000Z · score: 2 (2 votes)
Passing Troll Bridge 2018-02-25T08:21:17.000Z · score: 9 (1 votes)
Further Progress on a Bayesian Version of Logical Uncertainty 2018-02-01T21:36:39.000Z · score: 3 (2 votes)
Strategy Nonconvexity Induced by a Choice of Potential Oracles 2018-01-27T00:41:04.000Z · score: 1 (1 votes)
Open Problems Regarding Counterfactuals: An Introduction For Beginners 2017-07-18T02:21:20.000Z · score: 20 (6 votes)

Comments

Comment by diffractor on The rationalist community's location problem · 2020-09-30T09:54:26.100Z · score: 1 (1 votes) · LW · GW

Reno has 90F daily highs during summer. Knocking 10 degrees off is a nonneglible improvement over Las Vegas, though.

Comment by diffractor on Needed: AI infohazard policy · 2020-09-21T20:50:53.784Z · score: 16 (7 votes) · LW · GW

So, here's some considerations (not an actual policy)

It's instructive to look at the case of nuclear weapons, and the key analogies or disanalogies to math work. For nuclear weapons, the basic theory is pretty simple and building the hardware is the hard part, while for AI, the situation seems reversed. The hard part there is knowing what to do in the first place, not scrounging up the hardware to do it.

First, a chunk from Wikipedia

Most of the current ideas of the Teller–Ulam design came into public awareness after the DOE attempted to censor a magazine article by U.S. anti-weapons activist Howard Morland in 1979 on the "secret of the hydrogen bomb". In 1978, Morland had decided that discovering and exposing this "last remaining secret" would focus attention onto the arms race and allow citizens to feel empowered to question official statements on the importance of nuclear weapons and nuclear secrecy. Most of Morland's ideas about how the weapon worked were compiled from highly accessible sources—the drawings which most inspired his approach came from the Encyclopedia Americana. Morland also interviewed (often informally) many former Los Alamos scientists (including Teller and Ulam, though neither gave him any useful information), and used a variety of interpersonal strategies to encourage informational responses from them (i.e., asking questions such as "Do they still use sparkplugs?" even if he wasn't aware what the latter term specifically referred to)....

When an early draft of the article, to be published in The Progressive magazine, was sent to the DOE after falling into the hands of a professor who was opposed to Morland's goal, the DOE requested that the article not be published, and pressed for a temporary injunction. After a short court hearing in which the DOE argued that Morland's information was (1). likely derived from classified sources, (2). if not derived from classified sources, itself counted as "secret" information under the "born secret" clause of the 1954 Atomic Energy Act, and (3). dangerous and would encourage nuclear proliferation...

Through a variety of more complicated circumstances, the DOE case began to wane, as it became clear that some of the data they were attempting to claim as "secret" had been published in a students' encyclopedia a few years earlier....

Because the DOE sought to censor Morland's work—one of the few times they violated their usual approach of not acknowledging "secret" material which had been released—it is interpreted as being at least partially correct, though to what degree it lacks information or has incorrect information is not known with any great confidence.

So, broad takeaways from this: The Streisand effect is real. A huge part of keeping something secret is just having nobody suspect that there is a secret there to find. This is much trickier for nuclear weapons, which are of high interest to the state, while it's more doable for AI stuff (and I don't know how biosecurity has managed to stay so low-profile). This doesn't mean you can just wander around giving the rough sketch of the insight, in math, it's not too hard to reinvent things once you know what you're looking for. But, AI math does have a huge advantage in this it's a really broad field and hard to search through (I think my roommate said that so many papers get submitted to NeurIPS that you couldn't read through them all in time for the next NeurIPS conference), and, in order to reinvent something from scratch without having the fundamental insight, you need to be pointed in the exact right direction and even then you've got a good shot at missing it (see: the time-lag between the earliest neural net papers and the development of backpropagation, or, in the process of making the Infra-Bayes post, stumbling across concepts that could have been found months earlier if some time-traveler had said the right three sentences at the time.)

Also, secrets can get out through really dumb channels. Putting important parts of the H-bomb structure in a student's encyclopedia? Why would you do that? Well, probably because there's a lot of people in the government and people in different parts have different memories of which stuff is secret and which stuff isn't.

So, due to AI work being insight/math-based, security would be based a lot more on just... not telling people things. Or alluding to them. Although, there is an interesting possibility raised by the presence of so much other work in the field. For nuclear weapons work, things seem to be either secret or well-known among those interested in nuclear weapons. But AI has a big intermediate range between "secret" and "well-known". See all those Arxiv papers with like, 5 citations. So, for something that's kinda iffy (not serious enough (given the costs of the slowdown in research with full secrecy) to apply full secrecy, not benign enough to be comfortable giving a big presentation at NeurIPS about it), it might be possible to intentionally target that range. I don't think it's a binary between "full secret" and "full publish", there's probably intermediate options available.

Of course, if it's known that an organization is trying to fly under the radar with a result, you get the Streisand effect in full force. But, just as well-known authors may have pseudonyms, it's probably possible to just publish a paper on Arxiv (or something similar) under a pseudonym and not have it referenced anywhere by the organization as an official piece of research they funded. And it would be available for viewing and discussion and collaborative work in that form, while also (with high probability) remaining pretty low-profile.

Anyways, I'm gonna set a 10-minute timer to have thoughts about the guidelines:

Ok, the first thought I'm having is that this is probably a case where Inside View is just strictly better than Outside View. Making a policy ahead of time that can just be followed requires whoever came up with the policy to have a good classification in advance all the relevant categories of result and what to do with them, and that seems pretty dang hard to do especially because novel insights, almost by definition, are not something you expected to see ahead of time.

The next thought is that working something out for a while and then going "oh, this is roughly adjacent to something I wouldn't want to publish, when developed further" isn't quite as strong of an argument for secrecy as it looks like, because, as previously mentioned, even fairly basic additional insights (in retrospect) are pretty dang tricky to find ahead of time if you don't know what you're looking for. Roughly, the odds of someone finding the thing you want to hide scale with the number of people actively working on it, so that case seems to weigh in favor of publishing the result, but not actively publicizing it to the point where you can't befriend everyone else working on it. If one of the papers published by an organization could be built on to develop a serious result... well, you'd still have the problem of not knowing which paper it is, or what unremarked-on direction to go in to develop the result, if it was published as normal and not flagged  as anything special. But if the paper got a whole bunch of publicity, the odds go up that someone puts the pieces together spontaneously. And, if you know everyone working on the paper, you've got a saving throw if someone runs across the thing.

There is a very strong argument for talking to several other people if you're unsure whether it'd be good to publish/publicize, because it reduces the problem of "person with laxest safety standards publicizes" to "organization with the laxest safety standards publicizes". This isn't a full solution, because there's still a coordination problem at the organization level, and it gives incentives for organizations to be really defensive about sharing their stuff, including safety-relevant stuff. Further work on the inter-organization level of "secrecy standards" is very much needed. But within an organization, "have personal conversation with senior personnel" sounds like the obvious thing to do.

So, current thoughts: There's some intermediate options available instead of just "full secret" or "full publish" (publish under pseudonym and don't list it as research, publish as normal but don't make efforts to advertise it broadly) and I haven't seen anyone mention that, and they seem preferable for results that would benefit from more eyes on them, that could also be developed in bad directions. I'd be skeptical of attempts to make a comprehensive policy ahead of time, this seems like a case where inside view on the details of the result would outperform an ahead-of-time policy. But, one essential aspect that would be critical on a policy level is "talk it out with a few senior people first to make the decision, instead of going straight for personal judgement", as that tamps down on the coordination problem considerably.

Comment by diffractor on CO2 Stripper Postmortem Thoughts · 2020-09-08T20:02:28.910Z · score: 1 (1 votes) · LW · GW

Person in a room: - 35 g of O2/hr from room
Person in a room with a CO2 stripper: -35 g of O2/hr from room

How does the presence of a CO2 stripper do anything at all to the oxygen amount in the air?

Comment by diffractor on Introduction To The Infra-Bayesianism Sequence · 2020-09-05T05:01:29.794Z · score: 1 (1 votes) · LW · GW

Do you think this problem is essentially different from "suppose Omega asks you for 10 bucks. You say no. Then Omega says "actually I flipped a fair coin that came up tails, if it had come up heads, I would have given you 100 dollars if I predicted you'd give me 10 dollars on tails"?

(I think I can motivate "reconsider choosing heads" if you're like "yeah, this is just counterfactual mugging with belated notification of what situation you're in, and I'd pay up in that circumstance")

Comment by diffractor on Introduction To The Infra-Bayesianism Sequence · 2020-09-05T03:11:16.319Z · score: 1 (1 votes) · LW · GW

Maximin over outcomes would lead to the agent devoting all its efforts towards avoiding the worst outcomes, sacrificing overall utility, while maximin over expected value pushes towards policies that do acceptably on average in all of the environments that it may find itself in.

Regarding "why listen to past me", I guess to answer this question I'd need to ask about your intuitions on Counterfactual mugging. What would you do if it's one-shot? What would you do if it's repeated? If you were told about the problem beforehand, would you pay money for a commitment mechanism to make future-you pay up the money if asked? (for +EV)

Comment by diffractor on Basic Inframeasure Theory · 2020-09-01T04:58:47.146Z · score: 1 (1 votes) · LW · GW

Yeah, looking back, I should probably fix the m- part and have the signs being consistent with the usual usage where it's a measure minus another one, instead of the addition of two signed measures, one a measure and one a negative measure. May be a bit of a pain to fix, though, the proof pages are extremely laggy to edit.

Wikipedia's definition can be matched up with our definition by fixing a partial order where  iff there's a  that's a sa-measure s.t. , and this generalizes to any closed convex cone. I lifted the definition of "positive functional" from Vanessa, though, you'd have to chat with her about it.

We're talking about linear functions, not affine ones.  is linear, not affine (regardless of f and c, as long as they're in  and , respectively). Observe that it maps the zero of  to 0.

Comment by diffractor on Basic Inframeasure Theory · 2020-09-01T04:45:29.013Z · score: 1 (1 votes) · LW · GW

We go to the trouble of sa-measures because it's possible to add a sa-measure to an a-measure, and get another a-measure where the expectation values of all the functions went up, while the new a-measure we landed at would be impossible to make by adding an a-measure to an a-measure.

Basically, we've gotta use sa-measures for a clean formulation of "we added all the points we possibly could to this set", getting the canonical set in your equivalence class.

Admittedly, you could intersect with the cone of a-measures again at the end (as we do in the next post) but then you wouldn't get the nice LF-duality tie-in.

Adding the cone of a-measures instead would correspond to being able to take expectation values of continuous functions in , instead of in [0,1], so I guess you could reformulate things this way, but IIRC the 0-1 normalization doesn't work as well (ie, there's no motive for why you're picking 1 as the thing to renormalize to 1 instead of, say, renormalizing 10 to 10). We've got a candidate other normalization for that case, but I remember being convinced that it doesn't work for belief functions, but for the Nirvana-as-1-reward-forever case, I remember getting really confused about the relative advantages of the two normalizations. And apparently, when working on the internal logic of infradistributions, this version of things works better.

So, basically, if you drop sa-measures from consideration you don't get the nice LF-duality tie in and you don't have a nice way to express how upper completion works. And maybe you could work with a-measures and use upper completion w.r.t. a different cone and get a slightly different LF-duality, but then that would make normalization have to work differently and we haven't really cleaned up the picture of normalization in that case yet and how it interacts with everything else. I remember me and Vanessa switched our opinions like 3 times regarding which upper completion to use as we kept running across stuff and going "wait no, I take back my old opinion, the other one works better with this".

Comment by diffractor on Introduction To The Infra-Bayesianism Sequence · 2020-08-28T05:48:29.752Z · score: 1 (1 votes) · LW · GW

Can you elaborate on what you meant by locally distinguishing between hypotheses?

Comment by diffractor on Coronavirus: Justified Practical Advice Thread · 2020-03-01T23:35:21.435Z · score: 4 (5 votes) · LW · GW

If hospitals are overwhelmed, it's valuable to have a component of the hospital treatment plan for pneumonia on-hand to treat either yourself or others who have it especially bad. One of these is oxygen concentrators, which are not sold out yet and are ~$400 on Amazon. This doesn't deal with especially severe cases, but for cases which fall in the "shortness of breath, low blood oxygen" class without further medical complications, it'd probably be useful if you can't or don't want to go to a hospital due to overload. https://www.who.int/publications-detail/clinical-management-of-severe-acute-respiratory-infection-when-novel-coronavirus-(ncov)-infection-is-suspected mentions oxygen treatment as the first thing to do for low blood oxygen levels.

Comment by diffractor on (A -> B) -> A · 2020-02-15T06:35:15.343Z · score: 2 (2 votes) · LW · GW

I found a paper about this exact sort of thing. Escardo and Olivia call that type signature a "selection functional", and the type signature is called a "quantification functional", and there's several interesting things you can do with them, like combining multiple selection functionals into one in a way that looks reminiscent of game theory. (ie, if has type signature , and has type signature , then has type signature .

Comment by diffractor on Counterfactual Induction · 2019-12-19T07:45:05.299Z · score: 1 (1 votes) · LW · GW

Oh, I see what the issue is. Propositional tautology given means , not . So yeah, when A is a boolean that is equivalent to via boolean logic alone, we can't use that A for the exact reason you said, but if A isn't equivalent to via boolean logic alone (although it may be possible to infer by other means), then the denominator isn't necessarily small.

Comment by diffractor on Counterfactual Induction · 2019-12-18T20:21:02.188Z · score: 1 (1 votes) · LW · GW

Yup, a monoid, because and , so it acts as an identitity element, and we don't care about the order. Nice catch.

You're also correct about what propositional tautology given A means.

Comment by diffractor on Counterfactual Induction (Algorithm Sketch, Fixpoint proof) · 2019-12-18T08:17:42.580Z · score: 1 (1 votes) · LW · GW

Yup! The subscript is the counterfactual we're working in, so you can think of it as a sort of conditional pricing.

The prices aren't necessarily unique, we set them anew on each turn, and there may be multiple valid prices for each turn. Basically, the prices are just set so that the supertrader doesn't earn money in any of the "possible" worlds that we might be in. Monotonicity is just "the price of a set of possibilities is greater than the price of a subset of possibilities"

Comment by diffractor on Counterfactual Induction · 2019-12-18T06:58:05.392Z · score: 2 (2 votes) · LW · GW

If there's a short proof of from and a short proof of from and they both have relatively long disproofs, then counterfacting on , should have a high value, and counterfacting on , should have a high value.

The way to read is that the stuff on the left is your collection of axioms ( is a finite collection of axioms and just means we're using the stuff in as well as the statement as our axioms), and it proves some statement.

For the first formulation of the value of a statement, the value would be 1 if adding doesn't provide any help in deriving a contradiction from A. Or, put another way, the shortest way of proving , assuming A as your axioms, is to derive and use principle of explosion. It's "independent" of A, in a sense.

There's a technicality for "equivalent" statements. We're considering "equivalent" as "propositionally equivalent given A" (Ie, it's possible to prove an iff statement with only the statements in A and boolean algebra alone. For example, is a statement provable with only boolean algebra alone. If you can prove the iff but you can't do it with boolean algebra alone, it doesn't count as equivalent. Unless is propositionally equivalent to , then is not equivalent to , (because maybe is false and is true) which renders the equality you wrote wrong, as well as making the last paragraph incoherent.

In classical probability theory, holds iff is 0. Ie, if it's impossible for both things to happen, the probability of "one of the two things happen" is the same as the sum of the probabilities for event 1 and event 2.

In our thing, we only guarantee equality for when (assuming A). This is because (first two = by propositonally equivalent statements getting the same value, the third = by being propositionally equivalent to assuming , fourth = by being propositionally equivalent to , final = by unitarity. Equality may hold in some other cases, but you don't have a guarantee of such, even if the two events are disjoint, which is a major difference from standard probability theory.

The last paragraph is confused, as previously stated. Also, there's a law of boolean algebra that is the same as . Also, the intuition is wrong, should be less than , because "probability of event 1 happens" is greater than "probability that event 1 and event 2 happens".

Highlighting something and pressing ctrl-4 turns it to LaTeX.

Comment by diffractor on CO2 Stripper Postmortem Thoughts · 2019-12-01T23:34:47.690Z · score: 11 (4 votes) · LW · GW

Yup, this turned out to be a crucial consideration that makes the whole project look a lot less worthwhile. If ventilation at a bad temperature is available, it's cheaper to just get a heat exchanger and ventilate away and eat the increased heating costs during winter than to do a CO2 stripper.

There's still a remaining use case for rooms without windows that aren't amenable to just feeding an air duct outside, but that's a lot more niche than my original expectations. Gonna edit the original post now.

Comment by diffractor on CO2 Stripper Postmortem Thoughts · 2019-12-01T00:46:05.951Z · score: 2 (2 votes) · LW · GW

Also, a paper on extremely high-density algal photobioreactors quotes algal concentration by volume as being as high as 6% under optimal conditions. The dry mass is about 1/8 of the wet mass of algae, so that's 0.75% concentration by weight percent. If the algal inventory in your reactor is 9 kg dry mass (you'd need to waste about 3 kg/day of dry weight or 24 kg/day of wet weight, to keep up with 2 people worth of CO2, or a third of the algae each day), that's 1200 kg of water in your reactor. Since a gallon is about 4 kg of water, that's... 300 gallons, or 6 55-gallon drums, footprint 4 ft x 6 ft x 4 ft high, at a bare minimum (probably 3x that volume in practice), so we get the same general sort of result from a different direction.

I'd be quite surprised if you could do that in under a thousand dollars.

Comment by diffractor on CO2 Stripper Postmortem Thoughts · 2019-12-01T00:30:44.731Z · score: 2 (2 votes) · LW · GW

[EDIT: I see numbers as high as 4 g/L/day quoted for algae growth rates, I updated the reasoning accordingly]

The numbers don't quite add up on an algae bioreactor for personal use. The stated growth rate for chlorella algae is 0.6 g/L/day, and there are about 4 liters in a gallon, so 100 gallons of algae solution is 400 liters is 240 g of algae grown per day, and since about 2/3ds of new biomass comes from CO2 via the 6CO2+6H2O->C6H12O6 reaction, that's 160 g of CO2 locked up per day, or... about 1/6 of a person worth of CO2 in a 24 hour period. [EDIT: 1 person worth of CO2 in a 24 hour period, looks more plausible]

Plants are inefficient at locking up CO2 relative to chemical reactions!

Also you wouldn't be able to just have the algae as a giant vat, because light has to penetrate in, so the resulting reactor to lock up 1/6 [EDIT: 1] of a person worth of CO2 would be substantially larger than the footprint of 2 55-gallon drums.

Comment by diffractor on CO2 Stripper Postmortem Thoughts · 2019-12-01T00:21:36.060Z · score: 2 (2 votes) · LW · GW

I have the relevant air sensor, it'd be really hard to blind it because it makes noise, and the behavioral effects thing is a good idea, thank you.

It's not currently with me.

I think the next thing to do is build the 2.0 design, because it should perform better and will also be present with me, then test the empirical CO2 reduction and behavioral effects (although, again, blinding will be difficult), and reevaluate at that point.

Comment by diffractor on So You Want to Colonize The Universe Part 5: The Actual Design · 2019-08-23T05:59:57.495Z · score: 1 (1 votes) · LW · GW

Good point on phase 6. For phase 3, smaller changes in velocity further out are fine, but I still think that even with less velocity changes, you'll still have difficulty finding an engine that gets sufficient delta-V that isn't fission/fusion/antimatter based. (also in the meantime I realized that neutron damage over those sorts of timescales are going to be *really* bad.) For phase 5, I don't think a lightsail would provide enough deceleration, because you've got inverse-square losses. Maybe you could decelerate with a lightsail in the inner stellar system, but I think you'd just breeze right through since the radius of the "efficiently slow down" sphere is too small relative to how much you slow down, and in the outer stellar system, light pressure is too low to slow you down meaningfully.

Comment by diffractor on So You Want To Colonize The Universe Part 3: Dust · 2019-08-23T05:53:19.550Z · score: 1 (1 votes) · LW · GW

Very good point!

Comment by diffractor on 87,000 Hours or: Thoughts on Home Ownership · 2019-07-08T05:05:39.761Z · score: 5 (4 votes) · LW · GW

I'd be extremely interested in the quantitative analysis you've done so far.

Comment by diffractor on Open Problems Regarding Counterfactuals: An Introduction For Beginners · 2019-03-25T21:41:31.947Z · score: 12 (4 votes) · LW · GW

See if this works.

Comment by diffractor on So You Want to Colonize The Universe Part 4: Velocity Changes and Energy · 2019-03-02T18:17:30.135Z · score: 2 (2 votes) · LW · GW

I'm talking about using a laser sail to get up to near c (0.1 g acceleration for 40 lightyears is pretty strong) in the first place, and slowing down by other means.

This trick is about using a laser sail for both acceleration and deceleration.

Comment by diffractor on So You Want to Colonize The Universe Part 4: Velocity Changes and Energy · 2019-03-02T02:13:19.223Z · score: 2 (2 votes) · LW · GW

Yeah, I think the original proposal for a solar sail involved deceleration by having the central part of the sail detach and receive the reflected beam from the outer "ring" of the sail. I didn't do this because IIRC the beam only maintains coherence over 40 lightyears or so, so that trick would be for nearby missions.

Comment by diffractor on So You Want To Colonize The Universe Part 3: Dust · 2019-02-28T21:31:33.143Z · score: 6 (5 votes) · LW · GW

For 1, the mental model for non-relativistic but high speeds should be "a shallow crater is instantaneously vaporized out of the material going fast" and for relativistic speeds, it should be the same thing but with the vaporization directed in a deeper hole (energy doesn't spread out as much, it keeps in a narrow cone) instead of in all directions. However, your idea of having a spacecraft as a big flat sheet and being able to tolerate having a bunch of holes being shot in it is promising. The main issue that I see is that this approach is incompatible with a lot of things that (as far as we know) can only be done with solid chunks of matter, like antimatter energy capture, or having sideways boosting-rockets, and once you start armoring the solid chunks in the floaty sail, you're sort of back in the same situation. So it seems like an interesting approach and it'd be cool if it could work but I'm not quite sure it can (not entirely confident that it couldn't, just that it would require a bunch of weird solutions to stuff like "how does your sheet of tissue boost sideways at 0.1% of lightspeed".

For 2, the problem is that the particles which are highly penetrating are either unstable (muons, kaons, neutrons...) and will fall apart well before arrival (and that's completely dodging the issue of making bulk matter out of them), or they are stable (neutrinos, dark matter), and don't interact with anything, and since they don't really interact with anything, this means they especially don't interact with themselves (well, at least we know this for neutrinos), so they can't hold together any structure, nor can they interact with matter at the destination. Making a craft out of neutrinos is ridiculously more difficult than making a craft out of room-temperature air. If they can go through a light-year of lead without issue, they aren't exactly going to stick to each other. Heck, I think you'd actually have better luck trying to make a spaceship out of pure light.

For 3, it's because in order to use ricocheting mass to power your starcraft, you need to already have some way of ramping the mass up to relativistic speeds so it can get to the rapidly retreating starcraft in the first place, and you need an awful lot of mass. Light already starts off at the most relativistic speed of all, and around a star you already have astronomical amounts of light available for free.

For 4, there sort of is, but mostly not. The gravity example has the problem of the speeding up of the craft when it has the two stars ahead of it perfectly counterbalancing the backwards deceleration when the two stars are behind it. For potentials like gravity or electrical fields or pretty much anything you'd want to use, there's an inverse-square law for them, which means that they aren't really relevant unless you're fairly close to a star. The one instance I can think of where something like your approach is the case is the electric sail design in the final part. In interstellar space, it brakes against the thin soup of protons as usual, but nearby a star, the "wind" of particles streaming out from the star acts as a more effective brake and it can sail on that (going out), or use it for better deceleration (coming in). Think of it as a sail slowing a boat down when the air is stationary, and slowing down even better when the wind is blowing against you.

Comment by diffractor on So You Want to Colonize The Universe · 2019-02-28T21:10:48.895Z · score: 3 (3 votes) · LW · GW

Whoops, I guess I messed up on that setting. Yeah, it's ok.

Comment by diffractor on So You Want to Colonize The Universe Part 4: Velocity Changes and Energy · 2019-02-28T01:07:23.941Z · score: 3 (3 votes) · LW · GW

Actually, no! The activation energy for the conversion of diamond to graphite is about 540 kJ/mol, and using the Arrhenius equation to get the rate constant for diamond-graphite conversion, with a radiator temperature of 1900 K, we get that after 10,000 years of continuous operation, 99.95% of the diamond will still be diamond. At room temperature, the diamond-to-carbon conversion rate is slow enough that protons will decay before any appreciable amount of graphite is made.

Even for a 100,000 year burn, 99.5% of the diamond will still be intact at 1900 K.

There isn't much room to ramp up the temperature, though. We can stick to around 99%+ of the diamond being intact up to around 2100 K, but 2200 K has 5% of the diamond converting, 2300 K has 15% converting, 2400K has 45%, and it's 80 and 99% conversion of diamond into graphite over 10,000 years for 2500 K and 2600 K respectively.

Comment by diffractor on So You Want to Colonize The Universe · 2019-02-27T19:31:12.774Z · score: 1 (4 votes) · LW · GW

Agreed. Also, there's an incentive to keep thinking about how to go faster until the marginal gain in design by one day of thought speeds the rocket up by less than one day, instead of launching, otherwise you'll get overtaken, and agreeing on a coordinated plan ahead of time (you get this galaxy, I get that galaxy, etc...) to avoid issues with lightspeed delays.

Comment by diffractor on So You Want to Colonize The Universe · 2019-02-27T19:28:57.684Z · score: 3 (3 votes) · LW · GW

Or maybe accepting messages from home (in rocket form or not) of "whoops, we were wrong about X, here's the convincing moral argument" and acting accordingly. Then the only thing to be worried about would be irreversible acts done in the process of colonizing a galaxy, instead of having a bad "living off resources" endstate.

Comment by diffractor on So You Want to Colonize the Universe Part 2: Deep Time Engineering · 2019-02-27T18:08:20.973Z · score: 5 (4 votes) · LW · GW

Edited. Thanks for that. I guess I managed to miss both of those, I was mainly going off of the indispensable and extremely thorough Atomic Rockets site having extremely little discussion of intergalactic missions as opposed to interstellar missions.

It looks like there are some spots where me and Armstrong converged on the same strategy (using lasers to launch probes), but we seem to disagree about how big of a deal dust shielding is, how hard deceleration is, and what strategy to use for deceleration.

Comment by diffractor on So You Want to Colonize The Universe · 2019-02-27T17:57:20.690Z · score: 2 (2 votes) · LW · GW

Yeah, Atomic Rockets was an incredibly helpful resource for me, I definitely endorse it for others.

Comment by diffractor on What makes people intellectually active? · 2019-01-15T01:16:04.921Z · score: 11 (6 votes) · LW · GW

This doesn't quite seem right, because just multiplying probabilities only works when all the quantities are independent. However, I'd put higher odds on someone having the ability to recognize a worthwhile result conditional on them having an ability to work on a problem, then having the ability to recognize a worthwhile result, so the multiplication of probabilities will be higher than it seems at first.

I'm unsure whether this consideration affects whether the distribution would be lognormal or not.

Comment by diffractor on Dutch-Booking CDT · 2019-01-14T01:29:23.101Z · score: 1 (1 votes) · LW · GW

(lightly edited restatement of email comment)

Let's see what happens when we adapt this to the canonical instance of "no, really, counterfactuals aren't conditionals and should have different probabilities". The cosmic ray problem, where the agent has the choice between two paths, it slightly prefers taking the left path, but its conditional on taking the right path is a tiny slice of probability mass that's mostly composed of stuff like "I took the suboptimal action because I got hit by a cosmic ray".

There will be 0 utility for taking left path, -10 utility for taking the right path, and -1000 utility for a cosmic ray hit. The CDT counterfactual says 0 utility for taking left path, -10 utility for taking the right path, while the conditional says 0 utility for left path, -1010 utility for right path (because conditional on taking the right path, you were hit by a cosmic ray).

In order to get the dutch book to go through, we need to get the agent to take the right path, to exploit P(cosmic ray) changing between the decision time and afterwards. So the initial bet could be something like -1 utility now, +12 utility upon taking the right path and not being hit by a cosmic ray. But now since the optimal action is "take the right path along with the bet", the problem setup has been changed, and we can't conclude that the agent's conditional on taking the right path places high probability on getting hit by a cosmic ray (because now the right path is the optimal action), so we can't money-pump with the "+0.5 utility, -12 utility upon taking a cosmic ray hit" bet.

So this seems to dutch-book Death-in-Damascus, not CDTEDT cases in general.

Comment by diffractor on Failures of UDT-AIXI, Part 1: Improper Randomizing · 2019-01-08T03:43:24.721Z · score: 3 (2 votes) · LW · GW

Yes, UDT means updateless decision theory, "the policy" is used as a placeholder for "whatever policy the agent ends up picking", much like a variable in an equation, and "the algorithm I wrote" is still unpublished because there were too many things wrong with it for me to be comfortable putting it up, as I can't even show it has any nice properties in particular. Although now that you mention it, I probably should put it up so future posts about what's wrong with it have a well-specified target to shoot holes in. >_>

Comment by diffractor on Cooperative Oracles · 2018-12-05T05:23:15.854Z · score: 1 (1 votes) · LW · GW

It actually is a weakening. Because all changes can be interpreted as making some player worse off if we just use standard Pareto optimality, the second condition mean that more changes count as improvements, as you correctly state. The third condition cuts down on which changes count as improvements, but the combination of conditions 2 and 3 still has some changes being labeled as improvements that wouldn't be improvements under the old concept of Pareto Optimality.

The definition of an almost stratified Pareto optimum was adapted from this , and was developed specifically to address the infinite game in that post involving a non-well-founded chain of players, where nothing is a stratified Pareto optimum for all players. Something isn't stratified Pareto optimal in a vacuum, it's stratified Pareto optimal for a particular player. There's no oracle that's stratified Pareto optimal for all players, but if you take the closure of everyone's SPO sets first to produce a set of ASPO oracles for every player, and take the intersection of all those sets, there are points which are ASPO for everyone.

Comment by diffractor on Beliefs at different timescales · 2018-11-06T01:00:36.301Z · score: 3 (2 votes) · LW · GW

My initial inclination is to introduce as the space of events on turn , and define and then you can express it as .

Comment by diffractor on Beliefs at different timescales · 2018-11-05T00:14:47.198Z · score: 1 (1 votes) · LW · GW

The notation for the sum operator is unclear. I'd advise writing the sum as and using an subscript inside the sum so it's clearer what is being substituted where.

Comment by diffractor on Asymptotic Decision Theory (Improved Writeup) · 2018-10-29T21:50:53.040Z · score: 3 (2 votes) · LW · GW

Wasn't there a fairness/continuity condition in the original ADT paper that if there were two "agents" that converged to always taking the same action, then the embedder would assign them the same value? (more specifically, if , then ) This would mean that it'd be impossible to have be low while is high, so the argument still goes through.

Although, after this whole line of discussion, I'm realizing that there are enough substantial differences between the original formulation of ADT and the thing I wrote up that I should probably clean up this post a bit and clarify more about what's different in the two formulations. Thanks for that.

Comment by diffractor on Asymptotic Decision Theory (Improved Writeup) · 2018-10-25T20:54:42.492Z · score: 1 (1 votes) · LW · GW
in the ADT paper, the asymptotic dominance argument is about the limit of the agent's action as epsilon goes to 0. This limit is not necessarily computable, so the embedder can't contain the agent, since it doesn't know epsilon. So the evil problem doesn't work.

Agreed that the evil problem doesn't work for the original ADT paper. In the original ADT paper, the agents are allowed to output distributions over moves. I didn't like this because it implicitly assumes that it's possible for the agent to perfectly randomize, and I think randomization is better modeled by a (deterministic) action that consults an environmental random-number generator, which may be correlated with other things.

What I meant was that, in the version of argmax that I set up, if is the two constant policies "take blank box" and "take shiny box", then for the embedder where the opponent runs argmax to select which box to fill, the argmax agent will converge to deterministically randomizing between the two policies, by the logical inductor assigning very similar expected utility to both options such that the inductor can't predict which action will be chosen. And this occurs because the inductor outputting more of "take the blank box" will have converge to a higher expected value (so argmax will learn to copy that), and the inductor outputting more of "take the shiny box" will have converge to a higher expected value (so argmax will learn to copy that).

The optimality proof might be valid. I didn't understand which specific step you thought was wrong.

So, the original statement in the paper was

It must then be the case that for every . Let be the first element of in . Since every class will be seperated by at least in the limit, will eventually be a distribution over just . And since for every , , by the definition of it must be the case that .

The issue with this is the last sentence. It's basically saying "since the two actions and get equal expected utility in the limit, the total variation distance between a distribution over the two actions, and one of the actions, limits to zero", which is false

And it is specifically disproved by the second counterexample, where there are two actions that both result in 1 utility, so they're both in the same equivalence class, but a probabilistic mixture between them (as converges to playing, for all ) gets less than 1 utility.

Consider the following embedder. According to this embedder, you will play chicken against ADT-epsilon who knows who you are. When ADT-epsilon considers this embedder, it will always pass the reality filter, since in fact ADT-epsilon is playing against ADT-epsilon. Furthermore, this embedder gives NeverSwerveBot a high utility. So ADT-epsilon expects a high utility from this embedder, through NeverSwerveBot, and it never swerves.

You'll have to be more specific about "who knows what you are". If it unpacks as "opponent only uses the embedder where it is up against [whatever policy you plugged in]", then NeverSwerveBot will have a high utility, but it will get knocked down by the reality filter, because if you converge to never swerving, will converge to 0, and the inductor will learn that so it will converge to assigning equal expected value to and, and converges to 1.

If it unpacks as "opponent is ADT-epsilon", and you converge to never swerving, then argmaxing will start duplicating the swerve strategy instead of going straight. In both cases, the argument fails.

Comment by diffractor on Asymptotic Decision Theory (Improved Writeup) · 2018-09-28T05:22:26.498Z · score: 3 (2 votes) · LW · GW

I got an improved reality-filter that blocks a certain class of environments that lead conjecture 1 to fail, although it isn't enough to deal with the provided chicken example and lead to a proof of conjecture 1. (the subscripts will be suppressed for clarity)

Instead of the reality-filter for being

it is now

This doesn't just check whether reality is recovered on average, it also checks whether all the "plausible conditionals" line up as well. Some of the conditionals may not be well-formed, as there may be conditioning on low-or-zero probability events, but these are then multiplied by a very small number, so no harm is done.

This has the nice property that for all "plausibly chosen embedders" that have a probability sufficiently far away from 0, all embedders and that pass this reality filter have the property that

So all embedders that pass the reality filter will agree on the expected utility of selecting a particular embedder that isn't very unlikely to be selected.

Comment by diffractor on Reflective AIXI and Anthropics · 2018-09-27T20:11:27.160Z · score: 1 (1 votes) · LW · GW

I figured out what feels slightly off about this solution. For events like "I have a long memory and accidentally dropped a magnet on it", it intuitively feels like describing your spot in the environment and the rules of your environment is much lower K-complexity than finding a turing machine/environment that starts by giving you the exact (long) scrambled sequence of memories that you have, and then resumes normal operating.

Although this also feels like something nearby is actually desired behavior. If you rewrite the tape to be describing some other simple environment, you would intuitively expect the AIXI to act as if it's in the simple environment for a brief time before gaining enough information to conclude that things have changed and rederive the new rules of where it is.

Comment by diffractor on Reflective AIXI and Anthropics · 2018-09-27T20:01:04.519Z · score: 1 (1 votes) · LW · GW

Not quite. If taking bet 9 is a prerequisite to taking bet 10, then AIXI won't take bet 9, but if bet 10 gets offered whether or not bet 9 is accepted, then AIXI will be like "ah, future me will take the bet, and wind up with 10+ in the heads world and -20+2 in the tails world. This is just a given. I'll take this +15/-15 bet as it has net positive expected value, and the loss in the heads world is more than counterbalanced by the reduction in the magnitude of loss for the tails world"

Something else feels slightly off, but I can't quite pinpoint it at this point. Still, I guess this solves my question as originally stated, so I'll PM you for payout. Well done!

(btw, you can highlight a string of text and hit crtl+4 to turn it into math-mode)

Comment by diffractor on Asymptotic Decision Theory (Improved Writeup) · 2018-09-27T16:01:20.403Z · score: 1 (1 votes) · LW · GW

Yup, I meant counterfactual mugging. Fixed.

Comment by diffractor on Asymptotic Decision Theory (Improved Writeup) · 2018-09-27T08:06:03.342Z · score: 1 (1 votes) · LW · GW

I think I remember the original ADT paper showing up on agent foundations forum before a writeup on logical EDT with exploration, and my impression of which came first was affected by that. Also, the "this is detailed in this post" was referring to logical EDT for exploration. I'll edit for clarity.

Comment by diffractor on Reflective AIXI and Anthropics · 2018-09-26T00:09:27.053Z · score: 1 (1 votes) · LW · GW

I actually hadn't read that post or seen the idea anywhere before writing this up. It's a pretty natural resolution, so I'd be unsurprised if it was independently discovered before. Sorry about being unable to assist.

The extra penalty to describe where you are in the universe corresponds to requiring sense data to pin down *which* star you are near, out of the many stars, even if you know the laws of physics, so it seems to recover desired behavior.

Comment by diffractor on Cooperative Oracles · 2018-09-05T03:54:17.930Z · score: 3 (2 votes) · LW · GW

Giles Edkins coded up a thing which lets you plug in numbers for a 2-player, 2-move game payoff matrix and it automatically displays possible outcomes in utility-space. It may be found here. The equilibrium points and strategy lines were added later in MS Paint.

Comment by diffractor on Cooperative Oracles · 2018-09-02T22:51:28.607Z · score: 1 (1 votes) · LW · GW

The basic reason for the dependency relation to care about oracle queries from strategies is that, when you have several players all calling the oracle on each other, there's no good way to swap out the oracle calls with the computation. The trick you describe does indeed work, and is a reason to not call any more turing machines than you need to, but there's several things it doesn't solve. For instance, if you are player 1, and your strategy depends on oracle calls to player 2 and 3, and the same applies to the other two players, you may be able to swap out an oracle call to player two with player two's actual code (which calls players 1 and 3), but you can't unpack any more oracle calls into their respective computations without hitting an infinite regress.

Comment by diffractor on Cooperative Oracles · 2018-09-01T16:24:54.548Z · score: 1 (1 votes) · LW · GW

I'm not sure what you mean by fixing the utility function occurring before fixing the strategy. In the problem setup of a game, you specify a utility function machine and a strategy machine for everyone, and there isn't any sort of time or order on this (there's just a set of pairs of probabilistic oracle machines) and you can freely consider things such as "what happens when we change some player's strategies/utility function machines"

Comment by diffractor on Probabilistic Tiling (Preliminary Attempt) · 2018-08-07T23:53:21.192Z · score: 1 (1 votes) · LW · GW

Ah, the formal statement was something like "if the policy A isn't the argmax policy, the successor policy B must be in the policy space of the future argmax, and the action selected by policy A is computed so the relevant equality holds"

Yeah, I am assuming fast feedback that it is resolved on day .

What I meant was that the computation isn't extremely long in the sense of description length, not in the sense of computation time. Also, we aren't doing policy search over the set of all turing machines, we're doing policy search over some smaller set of policies that can be guaranteed to halt in a reasonable time (and more can be added as time goes on)

Also I'm less confident in conditional future-trust for all conditionals than I used to be, I'll try to crystallize where I think it goes wrong.

Comment by diffractor on Probabilistic Tiling (Preliminary Attempt) · 2018-08-07T23:19:46.375Z · score: 1 (1 votes) · LW · GW

First: That notation seems helpful. Fairness of the environment isn't present by default, it still needs to be assumed even if the environment is purely action-determined, as you can consider an agent in the environment that is using a hardwired predictor of what the argmax agent would do. It is just a piece of the environment, and feeding a different sequence of actions into the environment as input gets a different score, so the environment is purely action-determined, but it's still unfair in the sense that the expected utility of feeding action into the function drops sharply if you condition on the argmax agent selecting action . The third condition was necessary to carry out this step. . The intuitive interpretation of the third condition is that, if you know that policy B selects action 4, then you can step from "action 4 is taken" to "policy B takes the actions it takes", and if you have a policy where you don't know what action it takes (third condition is violated), then "policy B does its thing" may have a higher expected utility than any particular action being taken, even in a fair environment that only cares about action sequences, as the hamster dance example shows.

Second: I think you misunderstood what I was claiming. I wasn't claiming that logical inductors attain the conditional future-trust property, even in the limit, for all sentences or all true sentences. What I was claiming was: The fact that is provable or disprovable in the future (in this case, is ), makes the conditional future-trust property hold (I'm fairly sure), and for statements where there isn't guaranteed feedback, the conditional future-trust property may fail. The double-expectation property that you state does not work to carry the proof through, because the proof (from the perspective of the first agent), takes as an assumption, so the "conditional on " part has to be outside of the future expectation, when you go back to what the first agent believes.

Third: the sense I meant for "agent is able to reason about this computation" is that the computation is not extremely long, so logical inductor traders can bet on it.