Some Thoughts Are Too Dangerous For Brains to Think

WrongBot

15 Some Thoughts Are Too Dangerous For Brains to Think

13th Jul 2010

4 min read

15

[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.

Personal Blog

15

New Comment

Rendering 0/318 comments, sorted by

top scoring

(show more) Click to highlight new comments since: Today at 2:04 PM

Some comments are truncated due to high volume. (⌘F to expand all)Change truncation settings

Moderation Log

15 Some Thoughts Are Too Dangerous For Brains to Think

by WrongBot

13th Jul 2010

4 min read

318

15

A few examples (in approximately increasing order of controversy):

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...

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.

Personal Blog

15

Mentioned in

87Taking Ideas Seriously

New Comment

Rendering 0/318 comments, sorted by

top scoring

(show more) Click to highlight new comments since: Today at 2:04 PM

Some comments are truncated due to high volume. (⌘F to expand all)Change truncation settings

Moderation Log

More from WrongBot

Curated and popular this week

318Comments

318

Comment Permalink

mattnewport16y70

This is an example of a pretty different kind of thing to what WrongBot is talking about. It's a hack for rationing attention or a technique for avoiding distraction and keeping focus for a period of time. You read the email once your current time-critical priority was dealt with, you didn't permanently delete it. Such tactics can be useful and I use them myself. It is quite different from permanently avoiding some information for fear of permanent corruption of your brain.

I'm a little surprised that you would have thought that this example fell into the same class of things as WrongBot or I were talking about. Perhaps we need to define what kinds of 'dangerous thought' we are talking about a little more clearly. I'm rather bemused that people are conflating this kind of avoidance of viscerally unpleasant experiences with 'dangerous thoughts' as well. It seems others are interpreting the scope of the article massively more broadly than I am.

ABranco16y30

Or putting it differently:

One thing is to operationally avoid gaining certain data at a certain moment in order to better function overall. Because we need to keep our attention focused.
Another thing is to strategically avoid gaining certain kinds of information that could possibly lead us astray.

I'd guess most people here agree with this kind of "self-deception" that the former entails. And it seems that the post is arguing pro this kind of "self-deception" in the latter case as well, although there isn't as much consensus — so... (read more)

3Tyrrell_McAllister16y

I think that you can just twiddle some parameters with my example to see something more like WrongBot's examples. My example had a known deadline, after which I knew it would be safe to read the reports. But suppose that I didn't know exactly when it would be safe to read the reports. My current project is the sort of thing where I don't currently know when I will have done enough. I don't yet know what the conditions for success are, so I don't yet know what I need to do to create safe conditions to read the reports. It is possible that it will never be safe to read the reports, that I will never be able to afford the distraction of suppressing my brain's desire to compose responses. My understanding is that WrongBot views group-intelligence differences analogously. The argument is that it's not safe to learn such truths now, and we don't yet know what we need to do to create safe conditions for learning these truths. Maybe we will never find such conditions. At any rate, we should be very careful about exposing our brains to these truths before we've figured out the safe conditions. That is my reading of the argument.

See in context