Followup ToAre You Anosognosic?, The Strangest Thing An AI Could Tell You

Over this past weekend I listened to an episode of This American Life titled Pro Se.  Although the episode is nominally about people defending themselves in court, the first act of the episode was about a man who pretended to act insane in order to get out of a prison sentence for an assault charge.  There doesn't appear to be a transcript, so I'll summarize here first.

A man, we'll call him John, was arrested in the late 1990s for assaulting a homeless man.  Given that there was plenty of evidence to prove him guilty, he was looking for a way to avoid the likely jail sentence of five to seven years.  The other prisoners he was being held with suggested that he plead insanity:  he'd be put up at a hospital for several months with hot food and TV and released once they considered him "rehabilitated".  So he took bits and pieces about how insane people are supposed to act from movies he had seen and used them to form a case for his own insanity.  The court believed him, but rather than sending him to a cushy hospital, they sent him to a maximum security asylum for the criminally insane.

Within a day of arriving, John realized the mistake he had made and sought to find a way out.  He tries a variety of techniques:  engaging in therapy, not engaging in therapy, dressing like a sane person, acting like a sane person, acting like an incurably insane person, but none of it works.  Over a decade later he is still being held.

As the story unravels, we learn that although John makes a convincing case that he faked his way in and is being held unjustly, the psychiatrists at the asylum know that he faked his way in and continue to hold him anyway, though John is not aware of this.  The reason:  through his long years of documented behavior John has made it clear to the psychiatrists that he is a psychopath/sociopath and is not safe to return to society without therapy.  John is aware that this is his diagnosis, but continues to believe himself sane.

Similar to trying to determine if you are anosognosic, how do you determine if you are insane?  Some kinds of insanity can be self diagnosed, but in John's case he has lots of evidence (he has access to read all of his own medical records) that he is insane, yet continues to believe himself not to be.  To me this seems a level trickier than anosognosis, since there's no physical tests you can make, but perhaps it's only a level of difference significant to people but not to an AI.

Edited to add a footnote:  By "sane" I simply mean normative human reasoning:  the way you expect, all else being equal, a human to think about things.  While the discussion in the comments about how to define sanity might be of some interest, it really gets away from the point of the post unless you want to argue that "sanity" is creating a question here that is best solved by dissolving the question (as at least one commenter does).

New to LessWrong?

New Comment
18 comments, sorted by Click to highlight new comments since: Today at 1:16 PM

This is a bit off topic, but I'd agree that John is, indeed, sane. As far as I know, sociopaths generally are sane by most standards: they do not have delusions or compulsions, for example. On the other hand, that doesn't mean they're not dangerous, in the same way that an enemy soldier or a paperclip maximizer is dangerous. Similarly, people with bipolar disorder are usually sane, but sometimes need hospitalization anyway.

I'd tell John that he's not being held because he's crazy, he's being held because he's a danger to himself or others, and he's not leaving until that's changed.

Perhaps a little tangential, but an excellent book with a sociopathic protagonist is I Am Not A Serial Killer by Dan Wells.

What do you mean by people with bipolar disorder being sane?

I could understand the claim that depressed people have accurate beliefs, but are a danger to themselves, but you said bipolar. Manic stages definitely involve false beliefs and overconfidence. Maybe they'd be considered within the sane range if the overconfidence were merely verbalized. Acting on beliefs that lots of people verbalize is often insane.

Or maybe I my parse failed...an individual with bipolar is sometimes sane and sometimes insane. But I'd still call the individual insane.

Or maybe I my parse failed...an individual with bipolar is sometimes sane and sometimes insane. But I'd still call the individual insane.

And I'd call you wrong. I'd also forgive the potential offense both because the symptoms of bipolar II hypomania are less well known and because your err is asserting a definitive relationship when there is merely a significant correlation.

Bipolar II is limited to hypomania and excludes psychosis. It is certainly possible to have bipolar and nevertheless maintain beliefs, actions and verbalisations that are well within the bounds of 'sane'. You may just have periods of having an awful lot of energy, not much sleep, plenty of confidence and rather a lot more sex than usual.

I stand corrected.

"Sanity" is not well-defined, here.

There are plenty of people just as sociopathic as John, and just as dangerous as John but more so, who would not be considered insane or perceived as dangerous by society at large.

Most people in positions of power have strong sociopathic tendencies. It's just that many of them conform sufficiently well with society's expectations that they're not recognized as threats.

A couple stabs:

A person's revealed utility function is the utility function that seems to govern their actual decisions. If a person's revealed utility function passes some threshold of wackiness or changes drastically enough at a high enough frequency, we call that person "insane".

If a person's cognitive experience is very significantly different from others without them having significantly lower intelligence, and this manifests itself in their behavior and harms their instrumental rationality, they can be considered insane.

"wackiness" should not be part of even a "stab" towards making something "well-defined".

If a person's cognitive experience is very significantly different from others without them having significantly lower intelligence, and this manifests itself in their behavior and harms their instrumental rationality, they can be considered insane.

This is why neurotypicality is considered a pathology by some.

Define a function's wackiness is easy. If you don't believe me, suffer through the following paragraph, in which I demonstrate my cleverness in a remarkably economist-like manner.

Let's say a utility function goes from world-states to real numbers on the interval [-1, 1]. -1 is the worst thing you can imagine and 1 is the best. Your function periodically re-normalizes as the best or worst thing you can imagine changes. To compute two utility functions' wackiness with respect to each other, compute the root-mean-squared differences between them across all world-states they are both defined on. Define a function A(world-state) which is defined on all world-states for which at least half of the human revealed utility functions are defined on and for which the standard deviation in the human revealed utility functions' computed values is less than 0.2. Its value for any given world-state is the average of all humanity's revealed utility functions' values for that world state. Observing all humanity's revealed utility functions' wackiness with respect to A, we designate humans as "insane" if their revealed utility functions' wackiness with respect to A is more than two standard deviations above the average.

In other words, insane people want really different things than other people.

That's probably not a good definition though, because those people are more likely to be called weird than insane. Probably the fast-changing revealed utility function definition is a better one. For that you'd compute the wackiness of a person's current revealed utility function with respect to the one they had five minutes ago over the last four days and add all the wackinesses together. If this result is more than four standard deviations above the average they can be considered insane.

For that you'd compute the wackiness of a person's current revealed utility function with respect to the one they had five minutes ago over the last four days and add all the wackinesses together. If this result is more than four standard deviations above the average they can be considered insane.

I'm not sure that really captures most of what passes for 'insane'.

Most people in positions of power have strong sociopathic tendencies. It's just that many of them conform sufficiently well with society's expectations that they're not recognized as threats.

And when you do recognise a sociopath with power as a threat the smartest option is to stay the #@$@# away!

Use of the label 'insane', among other things, means "I have the social resources to call you insane and get away with it".

This question goes away if you taboo "sane". If you're really asking "are my deeply-held beliefs about my other deeply-held beliefs true", then you start to apply some of the techniques being explored here.

And still, you should accept that no bayesean estimate (including meta-beliefs) can rationally be 0 or 1, so there's always the chance that you're completely stuck in a fantasy.

[-][anonymous]15y40

Not sure if I should argue about sanity with someone who's name is Dagon. ;-)

Tabooing sane, I get "free from behaviors outlined in psychology books as insane". Is that against the rules of taboo, to use insane?

It seems to me that while there is a fuzzy line when we are trying to conceive of sanity/insanity, in the end it is socially decided upon, and I defer to the experts unless I have cause not to.

free from behaviors outlined in psychology books as insane

It seems to me that in defining it that way, you've removed the motivation for being concerned about whether oneself is insane.

[-][anonymous]15y10

Not necessarily. Ever seen the movie "A Beautiful Mind"? He had no idea his family and friends were figments of a schizophrenic imagination. Just reading about it in a textbook wouldn't have solved his problem, since he had not yet received any information persuading him that anything was fishy.

Edit: But my definition does change how one would go through evaluating whether one was insane. They'd read a book and do what they could to detect anything tricky, like anosognosia or schitzophrenia.

Edit: Once I'm used to commenting, maybe I'll edit less frequently. I apologize to anyone annoyed by this. I decided a more precise way of summarizing my response is a person can still be concerned about whether they have the capabilities to recognize the symptoms.

If I taboo "sane" in the sense used above, I get: typical human reasoning.

The problem here is the word sanity. Nobody thinks John is insane in the sense of being disconnected from reality. The doctors just think John is dangerous - a psycopath. They're using the word "insane" in the sense that it means "someone who needs to be locked up". John is either asserting that their invocation of that sense is inappropriate for somebody with his neural condition, or he is lying about himself, (which I'd say is more likely). Psycopaths have no great trouble diagnosing themselves. They just don't go around telling other people.

John is right though. He's not insane. He's just evil. Whether we ought to treat that in the same places we treat the insane is a good question.

Define 'sane', please?