[EDIT - While I still support the general premise argued for in this post, the examples provided were fairly terrible. I won't delete this post because the comments contain some interesting and valuable discussions, but please bear in mind that this is not even close to the most convincing argument for my point.]
A great deal of the theory involved in improving computer and network security involves the definition and creation of "trusted systems", pieces of hardware or software that can be relied upon because the input they receive is entirely under the control of the user. (In some cases, this may instead be the system administrator, manufacturer, programmer, or any other single entity with an interest in the system.) The only way to protect a system from being compromised by untrusted input is to ensure that no possible input can cause harm, which requires either a robust filtering system or strict limits on what kinds of input are accepted: a blacklist or a whitelist, roughly.
One of the downsides of having a brain designed by a blind idiot is that said idiot hasn’t done a terribly good job with limiting input or anything resembling “robust filtering”. Hence that whole bias thing. A consequence of this is that your brain is not a trusted system, which itself has consequences that go much, much deeper than a bunch of misapplied heuristics. (And those are bad enough on their own!)
In discussions of the AI-Box Experiment I’ve seen, there has been plenty of outrage, dismay, and incredulity directed towards the underlying claim: that a sufficiently intelligent being can hack a human via a text-only channel. But whether or not this is the case (and it seems to be likely), the vulnerability is trivial in the face of a machine that is completely integrated with your consciousness and can manipulate it, at will, towards its own ends and without your awareness.
Your brain cannot be trusted. It is not safe. You must be careful with what you put into it, because it will decide the output, not you. We have been warned, here on Less Wrong, that there is dangerous knowledge; Eliezer has told us that knowing about biases can cause us harm. Nick Bostrom has written a paper describing dozens of ways in which information can hurt us, but he missed (at least) one.
The acquisition of some thoughts, discoveries, and pieces of evidence can lower our expected outcomes, even when they are true. This can be accounted for; we can debias. But some thoughts and discoveries and pieces of evidence can be used by our underhanded, untrustworthy brains to change our utility functions, a fate that is undesirable for the same reason that being forced to take a murder pill is undesirable.
(I am making a distinction here between the parts of your brain that you have access to and can introspect about, which for lack of better terms I call “you” or “your consciousness”, and the vast majority of your brain, to which you have no such access or awareness, which I call “your brain.” This is an emotional manipulation, which you are now explicitly aware of. Does that negate its effect? Can it?)
A few examples (in approximately increasing order of controversy):
Identity Politics: Paul Graham and Kaj Sotala have covered this ground, so I will not rehash their arguments. I will only add that, in the absence of a stronger aspect of your identity, truly identifying as something new is an irreversible operation. It might be overwritten again in time, but your brain will not permit an undo.
Power Corrupts: History is littered with examples of idealists seizing power only to find themselves betraying the values they once held dear. No human who values anything more than power itself should seek it; your brain will betray you. There has not yet been a truly benevolent dictator and it would be delusional at best to believe that you will be the first. You are not a mutant. (EDIT: Michael Vassar has pointed out that there have been benevolent dictators by any reasonable definition of the word.)
Opening the Door to Bigotry: I place a high value on not discriminating against sentient beings on the basis of artifacts of the birth lottery. I’ve also observed that people who come to believe that there are significant differences between the sexes/races/whatevers on average begin to discriminate against all individuals of the disadvantaged sex/race/whatever, even when they were only persuaded by scientific results they believed to be accurate and were reluctant to accept that conclusion. I have watched this happen to smart people more than once. Furthermore, I have never met (or read the writings of) any person who believed in fundamental differences between the whatevers and who was not also to some degree a bigot.
One specific and relatively common version of this are people who believe that women have a lower standard deviation on measures of IQ than men. This belief is not incompatible with believing that any particular woman might be astonishingly intelligent, but these people all seem to have a great deal of trouble applying the latter to any particular woman. There may be exceptions, but I haven’t met them. Based on all the evidence I have, I’ve made a conscious decision to avoid seeking out information on sex differences in intelligence and other, similar kinds of research. I might be able to resist my brain’s attempts to change what I value, but I’m not willing to take that risk; not yet, not with the brain I have right now.
If you know of other ways in which a person’s brain might stealthily alter their utility function, please describe them in the comments.
If you proceed anyway...
If the big red button labelled “DO NOT TOUCH!” is still irresistible, if your desire to know demands you endure any danger and accept any consequences, then you should still think really, really hard before continuing. But I’m quite confident that a sizable chunk of the Less Wrong crowd will not be deterred, and so I have a final few pieces of advice.
- Identify knowledge that may be dangerous. Forewarned is forearmed.
- Try to cut dangerous knowledge out of your decision network. Don’t let it influence other beliefs or your actions without your conscious awareness. You can’t succeed completely at this, but it might help.
- Deliberately lower dangerous priors, by acknowledging the possibility that your brain is contaminating your reasoning and then overcompensating, because you know that you’re still too overconfident.
- Spend a disproportionate amount of time seeking contradictory evidence. If believing something could have a great cost to your values, make a commensurately great effort to be right.
- Just don’t do it. It’s not worth it. And if I found out, I’d have to figure out where you live, track you down, and kill you.
Just kidding! That would be impossibly ridiculous.
In the past I have largely agreed with the sentiment that truth and information are mostly good, and when they create problems the solution is even more truth.
But on the basis of an interest in knowing more, I sometimes try to seek evidence that supports things I think are false or that I don't want to be true. Also, I try to notice when something I agree with is asserted without good evidential support. And I don't think you supported your conclusions there with real evidence.
This reads more to me like prescriptive signaling than like evidence. While it is very likely to be the case that "IQ test results" are not the same as "human worth", it doesn't follow that an arbitrary person would not change their behavior towards someone who is "measurably not very smart" in any way that dumb person might not like. And for some specific people (like WrongBot by the admission of his or her own fears) the fear may very well be justified.
When I read Cialdinni's book Influence, I was struck by the number of times his chapters took the form: (1) describe mental shenanigan, (2) offer evidence that people are easily and generally tricked in this way (3) explain how it functions as a bias when manipulated and a useful heuristic in non-evil environments, (4) offer laboratory evidence that basic warnings to people about the trick offer little protective benefit, (5) exhort the reader to "be careful anyway" with some ad hoc and untested advice.
Advice should be supported with evidence... and sometimes I think a rationalist should know when to shut up and/or bail out of a bad epistemic situation.
Evidence from implicit association tests indicate that people can be biased against other people without even being aware of it. When scientists tried to measure the degree of "cognitive work" it takes to parse racist situations they found that observing overt racism against black people was mentally taxing to white people while observing subtle racism against black people racism was mentally taxing to black people. The whites were oblivious to subtle racism and didn't even try to process it because it happened below their perceptual awareness, overt racism made them stop and momentarily ponder if maybe (shock!) we don't live in a colorblind world yet. The blacks knew racism was common (but not universal) and factored it into their model of the situation without lots of trouble when racism was overt - the tricky part was subtle racism where they had to think through the details to understand what was going on.
(I feel safe saying that white people are frequently oblivious to racism, and are sometimes active but unaware perpetrators of subtle forms of racism because I myself am white. When talking about group shortcomings, I find it best to stick to the shortcomings of my own group.)
Based on information like this, I can easily imagine that I might learn a true (relatively general) fact, use it to leap to an unjustifiable conclusion with respect to an individual, have that individual be harmed by my action, and never notice unless "called on it".
But when called on it, its quite plausible that I'd leap to defend myself and engage in a bunch of motivated cognition to deny that I could possibly ever be biased... and I'd dig myself even deeper into a hole, updating the wrong way when presented with "more evidence". So it would seem that more information would just leave me more wrong than I started with, unless something unusual happened.
(Then, to compound my bad luck I might cache defensive views of myself after generating them in the heat of an argument.)
So it seems reasonable to me that if we don't have the time to drink largely then maybe we should avoid shallow draughts. And even in that case we should be cautious about any subject that impinges on mind killer territory because more evidence really does seem to make you more biased in such areas.
I upvoted the article (from -2 to -1) because the problems I have with it are minor issues of tone, rather major issues with the the content. The general content seems to be a very fundamental rationalist "public safety message", with more familiarity assumed than is justified (like assuming everyone automatically agrees with Paul Graham and putting in a joke about violence at the end).
I don't, unfortunately, know of any experimentally validated method for predicting whether a specific person at a specific time is going to be harmed or helped by a specific piece of "true information" and this is part of what makes it hard to talk with people in a casual manner about important issues and feel justifiably responsible about it. In some sense, I see this community as existing, in part, to try to invent such methods and perhaps even to experimentally validate them. Hence the up vote to encourage the conversation :-)
Those are good points.
What I was trying to encourage was a practice of trusting your own strength. I think that morally conscientious people (as I suspect WrongBot is) err too much on the side of thinking they're cognitively fragile, worrying that they'll become something they despise. "The best lack all conviction, while the worst are full of passionate intensity."
Believing in yourself can be a self-fulfilling prophecy; believing in your own ability to resist becoming a racist might also be self-fulfilling. There's plenty of evidence for co... (read more)