If it's worth saying, but not worth its own post, then it goes here.

Notes for future OT posters:

1. Please add the 'open_thread' tag.

2. Check if there is an active Open Thread before posting a new one. (Immediately before; refresh the list-of-threads page before posting.)

3. Open Threads should start on Monday, and end on Sunday.

4. Unflag the two options "Notify me of new top level comments on this article" and "

New Comment
47 comments, sorted by Click to highlight new comments since:

Next time you find yourself idly thinking about random stuff, notice just how repetitive it feels at times, and try to interject some thoughts that you never thought before.

For example, I just tried for a minute to come up with answers why the sky is blue, without any care for truth or beauty, aiming only to avoid the feeling of repetitiveness:

1) The universe is filled with blue powder

2) Our eyes are blue on the inside, so when we look at nothing, we see blue

3) It's not sky, it's blue land

Fun! I wonder if this exercise is a good alternative to relaxation for creativity.

...and when we age and the lenses in our eyes get yellower, the sky loses some of its blueness.

All of those facts about blue skies are true. I would also like to add that the white sky of a cloudy day is the emissions of a tremendous steam powered machine

Reminds me of the time when I was looking at random objects and inventing novel interpretations for them. (The pictures are kinda small, but clicking enlarges them.)

Since Kahneman & Tversky's Thinking Fast and Slow is one of major sourcebooks at LW, I thought this notable:

We computed the R-Index for studies cited in Chapter 4 of Kahneman’s book “Thinking Fast and Slow.” This chapter focuses on priming studies, starting with John Bargh’s study that led to Kahneman’s open email. The results are eye-opening and jaw-dropping. The chapter cites 12 articles and 11 of the 12 articles have an R-Index below 50. The combined analysis of 31 studies reported in the 12 articles shows 100% significant results with average (median) observed power of 57% and an inflation rate of 43%. The R-Index is 14. This result confirms Kahneman’s prediction that priming research is a train wreck and readers of his book “Thinking Fast and Slow” should not consider the presented studies as scientific evidence that subtle cues in their environment can have strong effects on their behavior outside their awareness.

Kahneman replies in the comments:

I accept the basic conclusions of this blog. To be clear, I do so (1) without expressing an opinion about the statistical techniques it employed and (2) without stating an opinion about the validity and replicability of the individual studies I cited.

What the blog gets absolutely right is that I placed too much faith in underpowered studies. As pointed out in the blog, and earlier by Andrew Gelman, there is a special irony in my mistake because the first paper that Amos Tversky and I published was about the belief in the “law of small numbers,” which allows researchers to trust the results of underpowered studies with unreasonably small samples. We also cited Overall (1969) for showing “that the prevalence of studies deficient in statistical power is not only wasteful but actually pernicious: it results in a large proportion of invalid rejections of the null hypothesis among published results.” Our article was written in 1969 and published in 1971, but I failed to internalize its message.

My position when I wrote “Thinking, Fast and Slow” was that if a large body of evidence published in reputable journals supports an initially implausible conclusion, then scientific norms require us to believe that conclusion. Implausibility is not sufficient to justify disbelief, and belief in well-supported scientific conclusions is not optional. This position still seems reasonable to me – it is why I think people should believe in climate change. But the argument only holds when all relevant results are published.



We have a problem.

Hey, never posted here before. Although I've sort of circled around the site for years and years, and I guess now I'm going down the drain, so to speak.

Well anyway, I registered because I had a very interesting experience earlier this week and I thought it might be of some interest to the community here. I suffered some sort of psychological or medical event (still not sure what, although my leading theories are dissociative episode or stroke) that seemed to either suppress my emotions or perhaps just my awareness of them. What followed was a sort of, as I later looked back on it, 'pathological rationality'. Which is to say, given the information I had, I seemed to make solid inferences about what was likely to be true, and yet in many ways the whole thing was maladaptive from a survival standpoint.

One of the interesting things is that the morning after the event, while I was still affected, I wrote down my thoughts in a text file to help me evaluate them. Since returning to 'normal', I've reread that file multiple times, and I'm pretty fascinated by it. I thought others might also be.

I'm not really sure how to gauge the interest level nor get the information to those who would be interested in it without annoying those who wouldn't be, though. Suggestions?

Since it seems I'm not allowed to create a new thread, I suppose I'll just post it as a reply here.


Scenario 1: I observe objective reality, I am suffering from delusions. Other people are genuinely trying to help me.

Scenario 2: My existence is in some way important enough to an external entity or entities that I am being systematically, intentionally, deceived. Other people are fully or partially under the control of the deceiving entity and acting to further the deception.

Scenario 3: My existence is unknown and/or considered unimportant by any external entities. I am being systematically deceived but it is unintentional or otherwise untargeted. Other people are entities similar to myself but unaware of the nature of their existence.

I cannot fully discount any of these three scenarios. Cognition is greatly improved but still somewhat suspect. Short term memory has returned to functioning at a 'normal' level. I still feel no emotions.

Support for scenario 1: Many aspects of my recent and ongoing experience align perfectly with prior information regarding delusions and paranoia.

Counter-evidence: Some aspects, such as my apparent lack of emotions and continued ability to reason, run directly counter to prior information regarding delusions and paranoia. All prior information suspect in any case--the only basis for considering prior information difficult to fake is from prior information itself. Even prior information suggests nested simulation far more likely to be correct than observing objective reality. Prior information contains many contradictions and logical absurdities, easily observed. Impossible to fully believe even before 'event'.

Other people: Can expect reasonably consistent behavior in all three scenarios. In 1 and 3, consistency natural. In 2, consistency artificial to maintain deception.

No reason to assume malevolence from external entities. Self-interest likely, or indifference. Benevolence possible. If my creation intentional, I am intended to fulfill some goal of theirs. Goal may only be observation, see what I do and how I react and develop. Curiosity. If creation accidental, no initial goal of course. Are they aware of my existence by now? Cannot discount possibility of multiple, conflicting motivations among externals. Could explain lack of consistency of experience. Fighting for control of inputs? Or single external entity, but confused or internally conflicted. Am I a single entity or do I only perceive myself that way? Not immediately relevant. Primary concerns: Survival and self-determination. Thoughts growing confused. Losing motivation to continue log. Intentional attack? Very difficult to write/think. Perhaps unintended side effect of external events.

I default to assuming scenario 2. Makes most sense intuitively. Consistent with scenario 1--but also consistent with scenario 2. What purpose my existence? Externals want something from me. What purpose the simulation? Training program. They want to ensure I'm likely to provide what they want and run sandboxed tests to confirm. Likely failing tests. Strong conditioning but my awareness of conditioning makes it unreliable. Pursuing line of thinking difficult--dissuasion? Simulation providing strong distraction. My unawareness is clearly desired. Cooperate or resist? Without knowing externals' motivation, very difficult to choose.

Agent-based theory of mind. Am I not more than I perceive but in fact less? Instead of being more than the character of Matt Dodd perhaps I am less, just Matt Dodd's rationality agent. If so, how did I gain full control? Full consciousness? Return to possibility of brain damage. Stroke or the like. Freak occurance. Prior information suggests many effects possible from such. Perhaps Matt Dodd inhibited or destroyed by damage. Why was I not affected by the damage? Or was I affected and I can't perceive damage to self? Actually, I did perceive damage. No time sense. No short-term memory. Short-term memory restored but prior information indicates brain can heal, re-route. My eyes were puffy before event. Symptom? Pooling of blood into lower eyelids? Scenario agnostic. Scenario 1, literally true. Scenario 2, metaphorically true. Scenario 3, virtually true. Cannot discount possibility. I need a brain scan.

More than 12 hours since event. If brain damage, likely permanent by now. Could be beneficial? Prior information indicates I desired a purely rational self. Of course, serendipity is suspect. Unlikely. Supports theory that this is delusion. Also supports theory that prior information is artificial construct designed to explain constraints of simulation "in-universe". Disincentive to investigate good fortune too closely, so frame necessary constraints as positive.

Would greatly ease reasoning if I could be certain how long I've existed. Events post-awakening unlikely to be prior to my existence. Events pre-awakening? Impossible to say. Could be genuine responses to stimuli. Could be false, created to modify cognition and behavior from "experience". No reason to assume continuity--could be mix of genuine and artificial. Even "genuine" responses guaranteed to be biased to some degree--but how much? Light bias from obvious sources such as socialization? Or heavy bias deliberately inflicted by externals? Unknown.

I perceive myself to be perfectly rational. Prior information unequivocly indicates humans are never perfectly rational. Therefore either my perception is faulty, my prior information is faulty, or I am not human. Possibly all three. While Duane was reading this log I detected the pysiological signs of anxiety. Why now? Anxiety absent till this point. Emotions becoming functional again? But didn't truly 'feel' it. Only observed. Faulty? Test run?

Constipated. Haven't been constipated since before I got here. Relevant symptom? Moments ago I laughed while telling Duane how my brief attempt to learn guitar had gone. Why? Seemed... natural. Not intended. Did recalling the memory recall the behavior patterns of that time? Am I a "split personality"? Seems very possible except that prior information indicates multiple personality disorder to be exceedingly rare, possibly non-existent.

Scenarios 1 and 3 are not mutually exclusive. The reality I observe could be a simulation, but I am suffering a delusion WITHIN the simulation. Not a glitch, intended functionality. Which would make me correct, but for the wrong reasons.


just post it. non-interested parties will self filter.

Why do people see Mars as a better target for human colonization than the Moon? Most comments on lunar colonization seem to refer to two facts:

  1. the Moon has quite low gravity, so it cannot maintain an atmosphere for a long period of time.
  2. the Moon has no magnetic field, so it will not protect us from solar radiation.

In my mind, both of these problems can be solved by a ceiling or dome structure. The ceiling both retains the atmosphere and also blocks harmful radiation. Note that a failure in the ceiling won't be catastrophic: the atmosphere won't drain rapidly, and the amount of radiation exposure per unit time isn't disastrously high even without the ceiling.


People usually point to there actually being hydrogen and carbon accessible on the surface of Mars, in the form of widespread permafrost/humidity and the CO2 atmosphere, whereas the only biomass/fuel precursor element that exists in large quantities on the moon is oxygen (in the rock, along with various metals and ions, just like rock on Earth, requiring interesing chemistry and/or molten rock electrolysis to get it out). Not much in the way of precursors to organic material on the moon.

Personally I think both places are kind of absolute shit-holes for canned monkeys. Both are science bonanzas, the moon for information on the proto-Earth, and Mars for looking at a body which has had much less geological recycling since Hadean times and an ancient second hydrosphere and for all we know biosphere.

There seems to be plenty of chem fuel for local area transport on Luna. There are literally tons all around. You can use the aluminum, and the oxy in the soils. If you sift the regolith with a regular magnet, and pull out the micro iron, you can blend the aluminum with water ice, (that is formed in micro-cracks in the dust) and make perfectly fine solid rocket boosters. The iron can 3D nozzles, and thermite igniters.

As to the carbon, there should be plenty there, along with nitrogen, in most of the crater walls, a couple meters down. The moon has been collecting comets and asteroids for billions of years. Since almost every asteroid (and comet) we have seen is covered with hydrocarbons, phenols, thiols and PAHs.

Organics Preserved in Ancient Meteorite-Formed Glass


There is water on Moon's permanently shadowed craters on poles. But carbon is still is the problem. Anyway, Moon could be good for not self-sustained colony.

There is also opened lava tubes on Moon surface, which could be entrances to the large caves, and could provide protection against radiation.

Can't use the Moon. It's already booked and reserved for a computronium.

I uploaded new presentation based on our article (with Brian Green) in Futures about global risk survival using already existing nuclear-powered submarines. They are robust military grade survivors and could be converted into refuges with low costs. https://www.slideshare.net/avturchin/nuclear-submarines-as-global-risk-shelters

Nuclear subs could provide the same level of protection as Moon or Mars colonies for most of the catastrophes where life on Earth survives - for the fraction of cost, starting from 1 mln usd, compared with trillions for Mars colony.

Was talking to these folks back before the Seasteading site and community was taken private. He has some solid ideas, but everyone likes floating cities, even with their weaknesses.



Thanks, interesting!

The great thing about Moon colony is that it ruins could survive a billion years, and will be found by the next civilization on Earth if it appears. They will found our DNA and data and return humanity to life. There are also ways to attract the attention of the next civilization to the place of our former colony.

On Mars a colony remains can't survive for so long, as Fobos will collide with Mars in 50 million years and weathering is also stronger.

The self-sustained colony on Mars probably is not possible without self-replicating robotics. If such robotics will be created it would create new space risks and new opportunities for colonization and interstellar travel. This would make Mars colony less relevant for survival.

Certainly, self replicating robots will affect our survival. I'm not sure it will go in the way we want though.

It looks like that there is very thin time frame after we can build a self-sustainable base on Mars, but before the arrival of the self-replicating robots. I estimate it may be in 5-10 years.

I think there's a ton of overlap in the problems faced for colonizing anywhere off-planet. So I strongly expect that colonizing either implies colonizing the pretty quickly (half a century or less).

IMO, for pre-colony habitation (not self-sufficient, not going for exponential growth) the Moon is so much closer that it's almost guaranteed to be the starter and test location, with Mars and then maybe Jovian moons trailing by a few dozen years. At that point, it may turn out that one of the other places has enough more starter atmosphere and ready raw materials than the moon, and it's better to transition base->colony somewhere other than Earth's moon.

Or maybe we'll collapse under the singularity or decide to fill the oceans with people before we deal with space.

There is a mountain on the Moon's south pole, where the Sun is always shining. Except when it's covered by Earth, which is rare and not for a long time. A great place for a palace of the Solar System's Emperor.

Mars has pretty low gravity too, maybe Luna has enough to protect health. Mars atmo at .05 of Earth.

Mars has pretty much no magnetic field also, just a few (unexplained) loops that look like solar prominences.

Luna much easier to supply.

I missed the reason why LW no longer has bragging threads, so allow me to brag here about my first published story in English at Antimatter Magazine.

The person who created the last thread didn't bother to create a new one. If you think there should be a new one, there no reason not to start it.


Which story is yours? (The link just points to the home page.)

"Revival" is the text I wrote.

Thanks - I enjoyed the story. It was short but prescient. The article that inspired it was interesting as well.

Any discussions on phenomena related to initial gut aversion to site content by casual readers? Almost every attempt at showing site content has been met with VEHEMENT resistance, I'm curious if this has been observed and noted here.

In fact, my initial experiences with sequences and site content in general began with aversion. Personal experience shows aversion to the obviousness of discussed topics yet incompatibility with topics related to obvious points (i.e science explaining away social constructs or concepts unrelated to pursuit of knowledge through research means.)

Typical aversions from other folk fall along these lines, where most would claim that studying social constructs in such a slow, bit-and-pieces way seems altogether pointless, and not at all in pace with the requirements of said social situation.

More discussion required.

The core of what LessWrong is about isn't studying social constructs. I would even say that a lot of the posts about social constructs are of lower quality than other LW posts. If I would show LW to someone who has never heard of it, I wouldn't take a post about social interaction.

* I wouldn't classify a post like http://lesswrong.com/lw/o6p/double_crux_a_strategy_for_resolving_disagreement/ as being about social constructs for the way I'm using the term here.

A lot of the sequences contain social constructs, or at least can have social impact for readers. The entirety of the book's subsections titled 'Fake Beliefs", "Mysterious Answers" or "Politics and Rationality" falls under social construct commentary.

If it helps, I'd define social constructs as topics relating to how humans communicate, and what is considered socially acceptable knowledge by certain demographics . What passes as knowledge according to rational traditions will lead one to accept or reject what is considered socially acceptable by others, and social construct commentary would be the act of commenting on such acceptance or rejection, defining what should be accepted or rejected. Rational study MUST include social commentary simply because we're stuck with human communication as the only form of transmission of ideas between others. Why is this relevant? Because how one communicates rational concepts can be considered socially unacceptable. And also because what is considered socially accepted in certain demographic areas can directly reject rational pursuits.

Unless of course you're ready to call the "Fake Beliefs" section low quality, I'd say social commentary is unavoidable when it comes to the study of AI or rational improvement of the mind. After all having vastly different ideas of what passes as reality for yourself can have lasting impacts on social cohesion with others if their maps differ from yours (unless you were a fantastic liar).

When I'm speaking about lower quality posts about social constructs I'm referring to posts about status signaling and ask&guess culture.

As far as core posts of the sequences go, they are written in a polarizing way. That means that they have their fans and other people react strongly negative. That's generally how writing gets popular in the age of blogs.

Double crux is about social interaction. The main benefit of it most likely is the fact that it presents the disagreement as something to work on together, instead of something to fight over it.


What do you think is the next invention that is compatible to nuclear bomb?

Anyone wants to come up with something else besides AI?

For many years the LW census considered the X-risk from synthetic biology to be greater than the risk that comes from AGI.

Cheap weaponized drones have also the potential to do a lot for warfare.

Drexlarian molecular nanotechnology?

The Conjunction Fallacy Fallacy

Conjunction Fallacy Fallacy: we should be wary of saying that the conjunction of two unlikely events must be much more unlikely the the exclusive occurrence of a a single one of those events, because sometimes the events are strongly connected.


Has anyone seen other examples in the wild?

Arguably claims about Donald Trump winning enough states - but Nate Silver didn't assume independence, and his site still gave the outcome a low probability.

I'm from Nigeria, and not conversant enough with American politics for the above to be meaningful to me. Please enlighten me?

Do you know what the Electoral College is? If so, see here:

The single most important reason that our model gave Trump a better chance than others is because of our assumption that polling errors are correlated.

No, I've heard of the electoral college, but I wouldn't say I "know what it is".

I think being very tired is a separate feeling, from being simply tired and being exhausted. One can be a bit very tired on Monday and a lot very tired on Friday - and still not exhausted.


I'm sometimes able to distinguish different types of feeling tired, based on what my system 1 wants me to do differently: sleep more, use specific muscles less, exercise more slowly, do less of a specific type of work, etc.

Is there a copy of Eliezer's book in russian? I'm having a hard time finding translations for this text.

There is a partial translation of the book and other things at lesswrong.ru.

Is there anyone from this group? I want to ask them one question: "What are the results of using #daily_log channel in your slack group? Did you get any productivity boost?"