Followup to: Beware of Other-Optimizing
Once upon a time, Seth Roberts (a professor of psychology at Berkeley, on the editorial board of Nutrition) noticed that he'd started losing weight while on vacation in Europe. For no apparent reason, he'd stopped wanting to eat.
Some time later, The Shangri-La Diet swept... the econoblogosphere, anyway. People including some respectable economists tried it, found that it actually seemed to work, and told their friends.
The Shangri-La Diet is unfortunately named - I would have called it "the set-point diet". And even worse, the actual procedure sounds like the wackiest fad diet imaginable:
Just drink two tablespoons of extra-light olive oil early in the morning... don't eat anything else for at least an hour afterward... and in a few days it will no longer take willpower to eat less; you'll feel so full all the time, you'll have to remind yourself to eat.
Why? I'm tempted to say "No one knows" just to see what kind of comments would show up, but that would be cheating. Roberts does have a theory motivating the diet, an elegant combination of pieces individually backed by previous experiments:
- Your metabolism has a set point, like the setting on a thermostat: when your weight is below the set point, you feel hungry; when your weight is above the set point, you feel full.
- But the set point is not a constant; it is raised and lowered by what you eat.
- This mechanism in turn seems to be regulated by a flavor-calorie association. (Possibly as a famine-storage mechanism that tries to store more resources when dense food sources are available.) If you eat something with flavor X, which is followed by your metabolism detecting a large source of calories, flavor X will (a) seem more appealing and taste better, and (b) will raise your set point whenever you eat items with flavor X.
- Your set point is always naturally dropping, but is raised by eating; usually these forces are in dynamic balance and your weight stays constant.
I'm not going to go into all the existing evidence that backs up each step of this theory, but the theory is very beautiful and elegant. The actual Shangri-La Diet is painfully simple by comparison: consume nearly tasteless extra-light olive oil, being careful not to associate it with any flavors before or after, to raise your body weight a little without raising your set point. Your body weight goes above your set point, and you stop feeling hungry. Then you eat less... and your weight drops... and your set point drops a little less than that... but then next morning it's time for your next dose of extra-light olive oil, which once again puts your (decreased) weight a bit above the set point. The regular dose of almost flavorless calories tilts the dynamic balance downward. That's the theory.
Many people, including some trustworthy econblogger types, have reported losing 1-2 pounds/week by implementing the actual actions of the Shangri-La Diet, up to 30 pounds or even more in some cases. Without expending willpower.
I tried it. It didn't work for me.
Now here's the frustrating thing: The Shangri-La Diet does not contain an obvious exception for Eliezer Yudkowsky. On the theory as stated, it should just work. But I am not the only person who reports trying this diet (and a couple of variations that Roberts recommended) without anything happening, except possibly some weight gain due to the added calories.
And here's the more frustrating thing: Roberts's explanation felt right. It's one of those insights that you grasp and then so much else snaps into place.
It explained that frustrating experience I'd often had, wherein I would try a new food and it would fill me up for a whole day - and then, as I kept on eating this amazing food in an effort to keep my total intake down, the satiation effect would go away.
It explained why I'd lost on the order of 50-60 pounds - with what, in retrospect, was very little effort - when I first moved out of my parents' house and to a new city and started eating non-Jewish food. In retrospect, I was eating an amazingly little amount each day, like 1200 calories, but without any feeling of hunger. And then my weight slowly started creeping up again, and no amount of exercise - to which (ha!) I'd originally attributed the weight loss - seemed able to stop it.
It's always hard to pick reality out of the gigantic morass of competing dietary theories. One of the elegant charms of Robert's hypothesis is that it helps explain why this is so - the mess of incoherent results. Any new diet will seem to work for a few months or weeks, you're losing weight and everything seems wonderful, you tell all your friends and they buy the same diet book, and then bam the flavor-calorie association kicks back in and you're back to hell. The number-one result of weight-loss science is that 95% of people who lose weight regain it.
(I haven't heard any complaints from people regaining weight they lost on the Shangri-La Diet, however - if it works for you at all, it seems to go on working. Most of the complaints on the forums are from people who suddenly plateau after losing 30 pounds, but who want to lose more. Or people like me, who try it, and find that it doesn't seem to do anything, or that we're gaining weight with no apparent loss of appetite.)
I have a pretty strong feeling - I don't know if I should trust it, since I'm not a dietary scientist - that Roberts's hypothesis is at least partially right. It makes a lot of data snap into focus. The pieces are well-supported individually.
But I don't think that Roberts has the whole story. There's something missing - something that would explain why the Shangri-La Diet lets some people control their weight as easily as a thermostat setting, and why others lose 30 pounds and then plateau well short of their goal, and why others simply find the Shangri-La diet ineffective. The Mystery of Shangri-La is not how the diet works when it does work; Roberts has made an excellent case for that. The question is why it sometimes doesn't work. There is a deeper law, I strongly suspect, that governs both the rule and the exception.
The problem is, though - and here's the really frustrating part - Roberts seems to think he does have the whole answer. If the diet doesn't work at first, his answer is to try more oil... which is a pretty scary answer if you're already gaining weight from the extra calorie intake! I decided not to go down this route because it didn't seem to work for the people on the forums who were reporting that the Shangri-La Diet didn't work for them. They just gained even more weight.
And what really makes this a catastrophe is that this theory has never been analyzed by controlled experiment, which drives me up the frickin' WALL. Roberts himself is a big advocate of "self-experimentation", which I suppose explains why he's not pushing harder for testing. (Though it's not like Roberts is a standard pseudoscientist, he's an academic in good standing.) But with reports of such drastic success from so many observers, some of them reliable, outside dietary scientists ought to be studying this. What the fsck, dietary scientists? Get off your butts and study this thing! NOW! Report these huge results in a peer-reviewed journal so that everyone gets excited and starts studying the exceptions to the rule!
It's awful; it seems like Roberts has gotten so close to burying the scourge Obesity, but the theory is still missing some final element, some completing piece that would explain the rule and the exception, and with that last piece it might be possible to make the diet work for everyone...
If we had a large-sized rationalist community going that had solved the group effort coordination problem, those of us who are metabolically disprivileged would be pooling resources and launching our own controlled study of this thing, and entering every conceivable variable we could report into the matrix, and hiring a professional biochemist to analyze our metabolisms before and afterward, and we would cryopreserve anyone who got in our way. You have no idea.
(Warning: Do not try the Shangri-La diet at home based on only the info here, there's a couple of caveats and I can't think offhand of a good complete description on the 'Net. Also you might want to reconsider the recommendation to use fructose in the sugar water route, because IIRC fructose has been shown to contribute to insulin resistance or something like that - sucrose may actually make more sense, despite the higher glycemic index.)
Continued in: Akrasia and Shangri-La
This suggests that the important factor in weight loss has nothing to do with any specific diet. Rather the key is the sudden shock to the endocrinological system that goes along with starting a new diet. Given any stable diet, your system will adapt to keep you at a certain weight. But if you constantly change your diet, your system will never be able to adapt.
Proposal: the meta-diet. Get 12 wonder diet books. Mark each month with a corresponding diet (Jan. is Atkin's, Feb is Shangri-La, ...) Every month, ditch the previous diet without a second thought and scrupulously adhere to the new one.
After reading all the comments and getting a lot more details about Eliezer's situation and the general responses to SLA, I have a theory:
SLA works by reducing appetite. The majority of the time, if you reduce appetite that causes people to eat less. When they eat less, they usually lose weight.
The problem is that SLA won't work if that link is broken. If you already weren't eating when you were hungry, then changing your hunger levels might not change how much you eat, which would result in you eating the same amount or if adding the oil doesn't reduce that amount you eat slightly more. In Eliezer's case, he already has so much willpower that he can break the link if he wants to, so SLA didn't solve the right problem. There are other ways to unlink that don't involve willpower, as well. For these people, SLA doesn't work. For another group, the link is severed past X pounds lost so it stops working.
Out of curiousity, on the specific subject of this diet: did you try blocking your sense of smell, preferably for the entire duration of the "no flavors" period?
As an enthusiastic home cook, the first thing that came to mind for me is that the vast majority of what we interpret as "flavor" is actually an interplay of taste and smell (hence why almost everything tastes like crap when you have nasal congestion). I recall that research has shown smell as having partiularly strong associative powers for memory, so it would not surprise me to find that it's actually a smell-calorie association at work, totally independent of what you actually put in your mouth.
Ergo, I would predict that experiencing strong smells around the same time as taking the flavorless calories would sabotage the effect catastrophically. Unfortunately for the pursuit of science, I have a naturally and stubbornly low bodyweight set point, so I can't test this personally.
That's one of the alternative avenues that Seth Roberts recommends - basically wearing nose clips for the rest of your life. I didn't actually try that, but maybe I'll go ahead and give it a shot.
So you have a theory personally developed and promoted by an enthusiastic individual, a whole slew of positival anecdotal evidence, but no actual proper experimental verification. Sound much like - ooh any complementary or alternative medical treatment you'd care to mention? Are you sure you're being fully rational here?
From Eliezer's other article:
As a diabetic (the kind caused by immunology, not the kind caused by diet), I am able to measure and experiment with insulin and blood sugar directly. I also think that Roberts is entirely wrong about why his diet works, and unless I see a study that says otherwise, I will believe that it would work equally well if you filled the olive oil with (metabolically inert) spices.
The real answer is that having fat in your system and being digested creates a buffer against blood sugar lows, which would make you feel hungry. If you eat some olive oil in the morning, the period in which it's being digested covers all three meals; on the other hand, fat eaten with dinner is mostly digested while you sleep. Normal appetite approximately matches energy expenditure, but blood sugar crash-driven eating is extra on top of that.
I'm just going to put this here because I was rather annoyed, after the fact, not to have been warned*: Drinking oil straight (which I tried for the first time this morning) is disgusting. It made me want to puke, although fortunately this had worn off by the end of the one-hour window when I wanted to eat. (Also, then I had a perfectly typical lunch which I enjoyed a normal amount and did not feel less motivated to eat than usual.)
*My model of what things are and are not disgusting to eat straight predicted this, but my model of how people talk about diets predicted that if it was in fact that disgusting, it would be a listed drawback of the diet.
I just noticed this little gem. I'm going to adopt it as my default expression when extreme declarations of uncompromising resolve are called for!
While controlled trials for SLA would be great, Roberts' advocacy of self-experimentation is awesome, and if it leads him to being biased against big studies...well...he is still adding to our collective knowledge.
Anyway, SLA kicked ass for me. I think I lost 8 lbs in the first couple weeks, 15 lbs in 2 or 3 months. But individual endocrinology varies widely and I can easily believe it doesn't work for everyone. Or maybe you're doing it wrong :). Also, even though SLA worked great for me at the beginning, it wore off over the course of months. I dunno... (read more)
Obvious test is obvious: Does IV calories work similarly?
The Shangri-La diet maybe works by bypassing the flavour-calorie association. If the calories go directly to your bloodstream; the bypass can't really get any cleaner.
What kind of rationalists are you? There is one way to lose weight with tons of research backing it, and perfectly valid molecular explanation how it works - one ECA pill every morning until you're done, if you're losing weight faster than 1kg/week definitely eat more as that's not very healthy.
You should behave like proper rationalists now, read some pubmed, order some pills, and lose as much weight as you want. No significant side effects observed, unlike "natural" dieting which causes hunger, loss of willpower, loss of energy etc. Your appetit... (read more)
I'm 86 kg (bmi ~27). I took your advice and tried taking one ECA pill every morning for the last few weeks and...I was gaining weight on it. I think I had a little loss of appetite right at first - along with a feeling of being "wired" - but the effect wore off after a day or two.
One confounding factor is that I normally consume a lot of caffeine (~200 mg) daily in the form of Diet Coke. I cut back a bit on the soda while taking ECA, so the change in my caffeine consumption while taking ECA compared to baseline was quite small - perhaps being a prior caffeine addict renders ECA less effective?
As with Shangri-la, one might conclude any of the following: (a) I just need to take more ECA (b) I just need to stick with it for longer - eventually the effect will kick in (c) It works for some people but not others for as-yet unidentified reasons (d) it doesn't work, and other factors explain the apparent success in some
As I understand it, ECA pills that contain actual ephedrine in amounts as high as you used can no longer be sold either in the US or in the EU - even the link you gave is now invalid because they've reformulated your pill. (The new Forza has "30 mg of Ephedra Extract" instead of 60 mg of ephedrine HCL; they recommend you take twice as many pills as before to get a similar effect.)
The good news for Americans is that we can still legally buy 25 mg Ephedrine. It can't be sold with weight-loss/bodybuilding claims but it's a legal over-the-counter treatment for asthma, if you don't buy too much of it at one time. So we can make our own ECA stack using three separate pills. I used this stack: 25mg Ephedrine (Vasopro), 200 mg Caffeine (No-Doz) and 325 mg aspirin.
And...it's working! You were correct to claim real Ephedrine would have a significant appetite suppressant effect - this was immediately apparent the first day I took it. It'd probably be stronger if I doubled the Eph dose to approach what you were taking - I might do that in a bit. It's too soon to tell whether I'll reach my long-term goals but things are definitely moving in the right direction!
UPDATE (2009): it's stil... (read more)
I've seen Roberts mention once or twice on his blog that he couldn't get a controlled experiment approved by the review board. (No details.) Also he seemed open to the diet just not working for some people.
Some variations haven't been mentioned here, like adding random combos of spices to your food to mix up the flavor. What I settled on, what worked for me without any unpleasantness drawing on willpower over time, was to pour flaxseed oil on toast and eat it noseclipped.
FWIW, one of the reasons Shangri-la didn't quite work for me at first is that I had acid reflux issues. My reflux belches apparently count as "a taste" and after I started taking Zantac to control them - and also drinking less carbonated soda - it worked much better. Another problem I had is an issue S-L has in common with some other diet systems such as Eat-Stop-Eat - any encouragement to "eat whatever you want" when on the diet/regimen is counterproductive if you're eating for any reason other than hunger. I sometimes eat due to bored... (read more)
Maybe just find a lot of reputable diets that might work, start on one, and then if you start regaining weight switch to something else. Not sure if this would work, but it could probably solve problems concerning getting used to it.
I've been doing informal research on diet and weight loss for 2 years now. I can say that there seems to be a survivorship bias problem. i.e. people seem to be more likely to report their early success than their later failure. Which is a problem since in diet and weight loss, long term results are what matters.
In fact, when I pester people for updates, I normally get either good news or no response. I don't recall even one person telling me that they fell off the wagon and regained everything.
...and then increase the dose to 4 tablespoons if that doesn't work, and then try some other stuff such as crazy-spicing your food if that doesn't work, according to page 62 and Chapter 6 of Roberts' "Shangri-La" Diet" book. I hope you at least tried the higher dose before giving up.
A more elegant explanation of the effectiveness of the diet would be that eating a calorically-dense food in the morning knocks your fat metabolism into gear.
I would like to take measurement of body temperatures while on the Shangri-La diet; I would expect body temperature to rise significantly from its nighttime low towards maximal resting temperaturen when olive oil was consumed (oil/fat being the most calorically dense macronutrient). Fat storage is very powerful, and very mysterious to doctors. If you're body doesn't feel comfortable losing weight, yo... (read more)
Other people have suggested similar things, but I'll take it a step farther: the issue may simply be fidelity of sensory input neurons, i.e. different things count as "having taste" for different people. I assure you, you could give me olive oil so lite that it glowed, and it would still have a very distinctive and strong taste to me.
This, I guess, is where the noseclip suggestion came from.
I have an (I think) better idea: "drink" the stuff by putting it in a (clean!) turkey baster, stick the turkey baster in the back of your throat, a... (read more)
Rethinking Thin has somewhat about what's known about the biology of hunger, satiation, and fat loss and retention. It's complicated. It's complicated even for "normal" people, and less is known about how it can vary or break.
I respect Seth's approach of self-experimentation, and I wish people for whom the Shangri-La diet doesn't work would poke around to see what weird thing they might find that works for them. However, I've seen Seth wildly over-generalize and over-recommend about the things that work for him. IIRC, he has mentioned that SLD wo... (read more)
Eliezer, do you eat more or less in response to low grade nausea? I have a hypothesis as to why the diet didn't work me for me. Mostly, the diet had no effect but occasionally I had appetite suppression with auxiliary symptoms that reminded me of the first trimester of pregnancy. In my case, the activated pathways seem to be related. I think maybe the diet works by making you nauseous, but since there's no flavor there's no obvious Garcia effect.
I'm not actually sure that the diet, as you've written it, would work even if the theory were complete. You say that an association is formed between flavor X and calories and that association with X controls the set point. But why would X be the dominant factor, when you're already eating flavors A, B, through to W whose contribution to the set point got you to the weight you started at? Does the book elaborate on how the association works?
As far as the oil diet, I tried it last year but didn't find much benefit. I had lost 40 pounds a year eralier and have kept it off since then through teeth-clenched, iron-willed, unceasing self-control. I tried oil for a few months and I can't really say it made it any easier. The oil tended to induce nausea which did suppress my appetite for a few hours, but it wasn't much fun feeling sick a lot.
You can alternatively drink sugar water in place of the oil, because sugar, in Roberts' model, does not have flavor.
By the way, "the set-point diet" is already taken - http://amzn.com/0061288675. (I tried this one and it did not work for me.)
This has been touched on indirectly in other comments, but it seems the simplest explanation of the failure mode described would be that the technique is just not being correctly performed, that there's some simple key variable that no one thinks to control for. Maybe you smell someone else in the building cooking breakfast, or brush your teeth with mint toothpaste, or use the wrong brand of oil.
On the note of self-testing vs. controlled experiment, has anyone here tried the polyphasic ("uberman") sleep cycle? Does anyone know of any controlled experiments, either self-administered or larger-scale, which I could look at? I was interested in trying it a few years ago, but dropped in in about 24 hours (before I could have really even been said to try it) due to microsleep in waking hours.
The background article for Shangri-La diet is titled What makes food fattening? A Pavlovian theory of weight control. This theory doesn't strike me as particularly Pavlovian. It might be more appropriate to call it a Powersian theory.
This post has generated a disproportionate number of comments. I think it illustrates the common struggles we all face in attempting to optimize our own behavior as well as that of others. At what point does other-optimizing become a case of trying to hard and lapsing into failure mode, a disutility loop if you will. The UC Berkeley writer Michael Pollan summed up his dietary advice in seven words: "Eat food, mostly plants, not too much." Or how about renowned nutritionist Marion Nestle: "East less, move more." Of course, one ... (read more)
FWIW, my diet gurus are mostly here: http://calorierestriction.org/
What I find interesting is this matches, almost exactly, the 30 pounds I lost when I decided to consistently take a multi-vitamin with every meal on the theory that hunger was caused (at least at times) by vitamin deficiencies, and maybe making sure I was flush with vitamins would help.
Worked great for a month or so - I lost (and have kept off) 30 pounds (Unfortunately that means I'm down to 310). Then it just kinda stopped - I haven't gone back up (indeed there have been moments when it acted like it might start going back down again, but so far I'm stuck... (read more)
The diet pretty obviously works because fat plays a huge role in satiety. If you can get a certain amount of fat in the lowest caloric form possible (olive oil, most likely), you won't be have to eat massively caloric things like bacon cheeseburgers in order to slake your hunger.
Still, good diet and exercise are the keys to staying thin. Satisfy your hunger by filling up on vegetables and lean protein. Exercise harder, eat less.
See Akrasia and Shangri-La, the sequel, for the reason why I wish there were some way I could strangle you over the Internet.
I am questioning the value of diet and exercise. Thermodynamics is technically true but useless, barring the application of physical constraint or inhuman willpower to artificially produce famine conditions and keep them in place permanently. You, clearly, are one of the metabolically privileged, so let me assure you that I could try exactly the same things you do to control your weight and fail. My fat cells would keep the energy that yours release; a skipped meal you wouldn't notice would have me dizzy when I stand up; exercise that grows your muscle mass would do nothing for mine.
Not for as far back as I can remember. One of the scarier parts of my childhood was having to hide food so that I could get something to eat on Yom Kippur, and hoping my parents never found out. I do remember at some point being too exhausted to walk either to or from the synagogue even with my father yelling at me - maybe that was when I was young enough to believe enough to actually fast?
I reasonably expect I would do better now, especially if I'd eaten all protein for a couple of days previous - my adult metabolism is not quite as bad as I remember it being in childhood, and my mind is a whole lot stronger. I'm not particularly inclined to test it, though.
What part of "None of the simple cute little solutions that seem like they really ought to work and do work for the metabolically privileged actually work for me" do you not understand? I've lived in a carefully crappy-food-free apartment and gained weight, and back when I was "losing weight thanks to willpower and exercise!" I ate Little Debbie's poison nuggets and lost weight.
You are ignorant of the governing laws. I don't know how to make it any clearer. Your mind is full of things that sound like good and virtuous truths of a fair and sensible universe where diligence is rewarded and laziness punished. These things are lies.
I can starve or think, not both at the same time.
Good thing you don't have that attitude about FAI.
Have you considered the possibility that you just did something wrong? Common knowledge says that you need to exercise for 20 minutes or more to do any fat burning, but I've read an interesting book that says aerobics don't actually improve your fitness or burn fat.
Specifically, the author claims that, yes, exercising for more than 20 minutes will cause you to burn fat because your sugar stores are exhausted. However, he says, this tells your body that it needs to keep fat around, since clearly you're doing things that need it. Thus, the long-term effect of long-duration aerobics is that you adapt to store fat more... which is why runners who stop running, quickly get fat.
What he suggests needs to happen instead is that you exercise in a way that rapidly consumes sugar, but doesn't dip into the fat stores, so that the adaptation response is to make the body lean towards storing food as sugar, and to convert stored fat to sugar.
His theory is th... (read more)
This touches on a general issue about free will.
In a world where everyone is sort of a jerk and says "Just shut up and exercise, you fatso!" there may be such a strong drive to avoid condemnation and low social status that you actually do shut up and exercise.
In the alternate world where everyone understands that it's not really your fault and you can't shout people into having more willpower and willpower is a sketchy concept anyway and accepts you for who you are - you will have no incentive to get better.
So occasionally I do tell people the equivalent of "shut up and exercise" for certain things, even though I know it doesn't work directly. It's a case by case basis, depending on how many opportunities the person is missing and how likely I think my advice is to seriously affect them.
I did shut up and exercise. It didn't work. That's the point at which you have a problem.
And for years I felt guilty and that I must be doing something wrong; and then I read about the Shangri-La diet and all these people losing 50 pounds with ease; and then it didn't work for me; and that was when I figured out that yes, I actually had put in a really serious try, and that what was really going on was that the laws just didn't work the good and virtuous and just way that everyone said they did.
Now maybe for other things... if willpower really does work... then telling people "Shut up and expend willpower" might be helpful. I've just gotten a lot more skeptical, now.
No... it... DOESN'T. I tried that. I ate a simple Paleo diet which consists of nothing except healthy foods; my staples were home-cooked turkey and bananas. I did it for months. I lost not a single pound.
You CANNOT BEGIN TO IMAGINE how much stuff that really truly seems like it ought to work simply DOES NOT WORK when you are metabolically disprivileged.
"Roberts seems to think he does have the whole answer. If the diet doesn't work at first, his answer is to try more oil... "
Coincidentally, I started looking into the diet a couple days before you posted this. I saw a few examples of him saying "try more oil", but didn't follow closely enough to see if that ever worked.
You make it sound like it doesn't, but how much evidence do you have on this?
You said it explained you losing 50lbs or so, but now it doesn't work for you. Why don't you try more variations until you do find something th... (read more)