Richard Hollerith

This is a comment on Eliezer’s series (from December?) on personhood, sentience and consciousness and their relation to morality. My comment relies on a knowledge of the cognitive skill sometimes known as mind reading or empathy. Mirror neurons are part of the implementation of that skill. By waiting till today to comment, I get to piggyback on Eliezer’s post Sympathetic Minds in which those things are explained.

In the series on personhood, Eliezer says that it is important when designing a superintelligence not to create a person as a side effect. For example, if the superintelligence has to predict the behavior of a person, Eliezer says that it is important that in computing the prediction, the AI does not simulate the person with such accuracy that the simulation itself constitutes a person.

My position is that the designer of a superintelligence does not have to worry about creating a new person. Contrary to what most people think, the whole question of whether an intelligent agent or a part of an intelligent agent is a person or whether it is conscious is irrelevant in most situations in which one is considering the far future or considering the use of extremely potent technological means like a superintelligent AI.

Any important decision is impinged on by thousands of factors, but turns on much fewer. If we build a superintelligence, we have to decide what goal to give it (including what ethical standards are always observed in the pursuit of the goal). The probability that the concept of personhood or consciousness is useful or important in making that decision is IMHO so low as to be not worth thinking about.

In Sympathetic Minds, Eliezer describes the empathy-sympathy system of the human brain. Consider what the empathy-sympathy system feels like from the inside. Fred is palling around with George. George stubs his toe. Fred’s visual cortex captures visual evidence of the accident and transmits information about George’s somatic state to mirror neurons in his insula and his somatic sensory cortex, which report a somatic state very similar to the somatic state being reported by George’s insula and somatic sensory cortex — probably minus some element of keenness or immediacy. “That’s gotta hurt,” Fred says.

If OTOH an intelligent giant cockroach incurs an injury within Fred’s field of vision, Fred’s empathy-sympathy system does not trigger. Ditto if a non-humanoid robot incurs an injury.

So, let us ask Fred, Why is that? Unless he is especially wise or sophisticated, Fred is likely to explain that George is a person whereas the giant intelligent cockroach is not. George is sentient; George is conscious.

Dear reader, there have been dozens of posts and comments on Overcoming Bias about consciousness and personhood. No one has provided a definition despite my having explicitly asked for one.

Well, I hereby propose a definition. I propose that consciousness or personhood is what the operation of the empathy-sympathy system feel like from the inside.

Let us take a few paragraphs to describe the empathy-sympathy system.

A significant fraction of the human brain is devoted to circuitry that monitors somatic state, e.g., the somatic sensory cortex, the insula, much or most of the cingulate cortex and parts of the limbic system and brain stem.

These circuits are devoted to questions like, How full is the bladder of the human whose brain this is? Is peeing the most efficacious use of the next few minutes? Does the human have an infection? If so, is it dire enough that it is time for the human to leave the tribe and start foraging desperately for substances that might have antibiotic properties? How much metabolic energy can the person produce at the current time? Might the human’s last meal have included a toxicant? Etc, Etc.

That is not the empathy-sympathy system; one might call it the body-sensing or self-monitoring system. Once the system is fixed in the human genome, it is possible for natural selection to repurpose it for understanding other individuals of the same species. (The repurposing involves mirror neurons, whose original purpose might have been to help he individual learn skills from others.) That is the empathy-sympathy system.

(In addition to somatic state, the human empathy-sympathy system seems to be able to pick up on another’s social state, on generalized cognitive states like confusion and surprise, on the basic emotions like anger and fear and on the social emotions, e.g., shame, embarassment and contempt.)

I propose the following definition: a “person” or a “conscious agent” is an agent whose somatic, social, cognitive and emotional state can be modeled or perceived by the human empathy-sympathy system.

(The empathy-sympathy system of certain humans will be more perceptive than that of others, and so whether an agent is recognized by the system will depend on which human’s system it is, but despite individual variation, there will be enough similiarities to produce the widespread beliefs described below.)

So, for example, the reason a cockroach is usually considered not-a-person is that the human neurological machinery for empathy and sympathy cannot perceive much at all about the somatic or social state of the cockroach: the cockroach’s body and brain and natural history are too different from the human body and brain and natural history, so the output of the empathy-sympathy system is, “I see no person here from which to extract somatic information”.

And “consciousness” is the information thus extracted.

A nice analogy is the tone a fighter pilot hears when one of his plane’s missiles has locked onto what the designers of the missile defined as a valid target, e.g., the heat signature of the exhaust of an enemy fighter. To be an exact analogy, the missile or the plane would have to relay to the pilot many bits of information about the “somatic state” of the enemy fighter, not just whether it has been detected.

Consciousness, sentience or personhood, in other words, is what the empathy-sympathy system feels like from the inside.

And humans tend to get too fundamentalist about consciousness.

For example, many humans (even ones with PhDs in physics) have the mistaken belief that consciousness is a fundamental substance of the universe, much like the quark is or like gravity is.

Equally mistaken is the idea that consciousness, sentience or personhood is a fundamental substance, factor or principle in morality.

Consider the proposition that whether an intelligent agent has intrinsic moral value depends on whether the agent is a person or not. Taboo the word “person” and we have, “Whether an intelligent agent has intrinsic moral value depends on whether a human (which human?) can use his or her neurological machinery for empathy and sympathy to determine the somatic, social, emotional and basic cognitive state of the agent.”

As I have explained elsewhere, I believe that systems of terminal values should be subject to Occam’s Razor. (Moreover, there is nothing that would count as evidence for or against a system of terminal values.) That is the argument against the preceding proposition that is most convincing to me: the hypothesis has unnecessary algorithmic complexity — just as for example the hypothesis that there is an invisible dragon living in my garage has unnecessary algorithmic complexity.

But there is another argument, and I might as well include it here. Whether the human empathy-sympathy system reports, “There is a person over there,” depends on many particulars. For example, I am not an expert on the empathy-sympathy system, but it strikes me as very likely that the presence of eyebrows whose color is distinct from the surrounding skin makes it significantly more likely that the empathy-sympathy system will pick up enough information to give off the sense that there is a person there. Remove an individual’s eyebrows, lower the probability that the individual will be perceived as a person. (To be considered a non-person, the individual will probably have other severe handicaps besides the lack of eyebrows.) Conversely, add eyebrows to a humanoid robot, increase the probability that the robot will be perceived as a person.

But you see, most of the people who believe that personhood, sentience or consciousness is fundamental to morality also believe that whether an agent deserves to be treated as a person is independent of such superficialities as whether the agent has eyebrows, which contradicts what I just said. I believe we should ignore the moral opinions of these people until they resolve the contradiction or until they supply an alternative definition of personhood or consciousness.

So there is another argument against the moral proposition that whether an agent is a person is somehow filled with moral portent. Again, I consider the argument from Occam’s Razor stronger, but I thought that one worth mentioning.

IIRC, one of the 2 area’s of the human brain most essential for language (Broca’s or Wernicke’s, I do not recall which) has an analog in the chimp brain, and IIRC the chimp analog is part of the chimp’s empathy-sympathy system. in other words, evidence from comparative neuroanatomy suggests that the human capacity for language evolved from the primate empathy-sympathy system.

Well, that helps explain why most humans mistakely believe that consciousness is a fundamental substance or factor of reality or morality, as follows:

Either language pervades the human brain and human mind or it does not.

If it does, and if language is part of the empathy-sympathy system, well, there is your explanation for why humans find it hard to perceive consciousness objectively or correctly.

If it is does not, that is, if there are subsystems of the human brain and the human mind in which language plays no role, then it is at least the case that the the parts of the brain and mind involved in saying and writing things like “I believe consciousness is fundamental to morality” depend heavily on language.

So there is an explanation for why most people have the false belief that consciousness, sentience or personhood is somehow central to morality — and why people like to talk about those concepts without supplying a definition even after a definition has been asked for.

Warning: stating that you believe that consciousness is an illusion and is irrelevant to morality will probably get you perceived as a wierdo or a moral monster by many people. (Richard Hollerith is a pseudonym to reduce the negative reputational and social effects of my opinions on my personal life.) There are many more things I can say about protecting yourself from the negative personal effects of the ethical system described in this blog, but I will hold those things for people who contact me for more information and who demonstrate at least some sympathy for my system of valuing things. (And please try to ask specific questions that can be answered without my having to write and write and write or talk and talk and talk.)

Tags: machine ethics

This entry was posted on Friday, January 23rd, 2009 at 6:41 am and is filed under Uncategorized. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.