Two straw men fighting

Um.

Sometime ago I posted to decision-theory-workshop an idea that may be relevant here. Hopefully it can shed some light on the "solution to free will" generally accepted on LW, which I agree with.

Imagine the following setting for decision theory: a subprogram that wants to "control" the output of a bigger program containing it. So we have a function world() that makes calls to a function agent() (and maybe other logically equivalent copies of it), and agent() can see the source code of everything inclucing itself. We want to write an implementation of agent(), without foreknowledge of what world() looks like, so that it "forces" any world() to return the biggest "possible" answer (scare quotes are intentional).

For example, Newcomb's Problem:

def world():
   box1 = 1000
   box2 = (agent() == 2) ? 0 : 1000000
   return box2 + ((agent() == 2) ? box1 : 0)

Then a possible algorithm for agent() may go as follows. Look for machine-checkable mathematical proofs (up to a specified max length) of theorems of the form "agent()==A implies world()==U" for varying values of A and U. Then, after searching for some time, take the biggest found value of U and return the corresponding A. For example, in Newcomb's Problem there are easy theorems, derivable even without looking at the source code of agent(), that agent()==2 implies world()==1000 and agent()==1 implies world()==1000000.

The reason this algorithm works is very weird, so you might want to read the following more than once. Even though most of the theorems proved by the agent are based on false premises (because it is logically impossible for agent() to return a value other than the one it actually returns), the one specific theorem that leads to maximum U must turn out to be correct, because the agent makes its premise true by outputting A. In other words, an agent implemented like that cannot derive a contradiction from the logically inconsistent premises it uses, because then it would "imagine" it could obtain arbitrarily high utility (a contradiction implies anything, including that), therefore the agent would output the corresponding action, which would prove the Peano axioms inconsistent or something.

To recap: the above describes a perfectly deterministic algorithm, implementable today in any ordinary programming language, that "inspects" an unfamiliar world(), "imagines" itself returning different answers, "chooses" the best one according to projected consequences, and cannot ever "notice" that the other "possible" choices are logically inconsistent with determinism. Even though the other choices are in fact inconsistent, and the agent has absolutely perfect "knowledge" of itself and the world, and as much CPU time as it wants. (All scare quotes are, again, intentional.)

Please try to write posts that show an awareness of the existing literature on the subject from within Less Wrong.

I generally like this post, and am unsure why it was voted down. However, I think that you need to separate "not useful" from "not true"- while it may or may not be true that neither is particularly useful in real life, under the definitions accepted by LW, both are almost certainly true.

I would like to see reference to "dissolving the question".

To predict anything really sizable, like for instance, how the earth came to be as it is, or even how little-old-me became what I am, or even why I did a particular thing a moment ago, would take more resources and time than can be found in the life of our universe.

Surely if the universe is deterministic, "the resources and time [that] can be found in the life of the universe" provides an upper bound on what you need to predict anything. Since, after all, the universe is 'predicting' it just fine without exceeding those requirements.

There's plenty of posts to be written on this topic, but this one needs a bit more work. References to the sequences, especially the Reductionism and Mind Projection Fallacy sections and stating what parts you disagree with or are expanding upon is a good idea.

More specific problems with the post:

• I don't think "a robust consensus answer" is what I'm hoping for - I'd rather have actual truth (though I appreciate when truth and consensus converge, it can take awhile).

• I like the rock analogy a lot, but you don't go far enough. We remove the rock after it's fallen, and we take steps to prevent it (or others) falling there again. Why wouldn't we take the same approach to humans? Remove those that can't be altered not to offend.

• Questions about individual vs group do not have "no good answer". "Shut up and multiply" is a pretty good answer to the vast majority of them (though I wish Eliezer had said "calculate" instead, as "multiply" sends my brain to species reproduction first before I remember the context). Recognizing the difference between the outcome you want and the signal you want to send is often necessary as part of the calculation of course.

• We need to start thinking of ourselves as whole beings, one entity from head to toe: brain and body, past and future, from birth to death. Wow, no. The tone is a bit condescending, but that's fixable. Much worse, it's simply not right, or at least very hard to justify. It may well be that what I call "me" is a set of distinct and shifting subentities, currently implemented in brain and body, with partial-at-best continuity from well before birth to a future beyond what will likely be called death.

The illusion of free will is an artifact of the incomplete knowledge of the mind's knowledge of the brain. It is not practical for an organism to evolve a brain to take be aware of its own functioning on the physical level of the decision making. An accurate simulation of a mind need not rely on a brain at all. We hope.

While we can say that actions are a result of purely physical processes, it is necessary to create abstract models of other people's projected actions in order to influence them. In recent years we have developed electromagnetic methods of overriding volition, but that approach is surely less efficient than persuasion.

My point is that neurology and psychology are different disciplines, and while they do overlap they do not need to converge but instead to conspire.

As for the moral thread of the post, rationally applied behavior modification ought take both into account. I am not sure what societal responses the post would suggest be changed, but I do believe that some moral truths are self-evident. {I am strongly opposed to destroying complexity without cause.}

I hope that within my lifetime mind will be more easily separate from brain through simulation and emulation. I suspect that new environments will be created in which action without consequence will be possible. I look forward to new means of communication which will muddle questions of identity and uniqueness (in a good way).

I would rather people look upon their bodies and brains as temporary vehicles for consciousness, and that they would be encouraged to find replacements as soon as possible. The inevitability of death is just a meme.

@ orthonormal

you said- I agree. But I think that there is actually some feature of the (deterministic) act of choosing which leads a person to falsely believe that their choice is nondeterministic, and that by analyzing this we learn something interesting and important about cognition.

Very true. so what do you make of reconciling the two? Do we castigate them both in hopes of finding something out that is hiding in the shadows? The nexus of the matter is "belief" and in order to have a sound belief one should know as many facts about the subject as possible. I listened to a long discourse given by Dennet who is a avid compatibilist, he presented an extremely weak argument with nothing to back up his claims, now when i read "the illusion of free will" by wegner its nothing but proof.

Now of course we can poke holes all day in theories derived from test studies. But by what else can we as humans deduct solid reasoning if we don't take what evidence is available to us. To me discussing this topic is not about fascination, its about getting the truth. I might be that crazy to think it's available.

@Thomblake sorry about the message thing. Im still getting used to how this site works..

You substantiate analogies with proof. Basically im saying that your analogies don't hold water perhaps i'm using confusing vernacular.

Let me say one thing before moving on. I hate debating just to debate, for me when i involve myself in a debate it is to gain more insight. So i am totally open to your point of view if it sheds some light on this subject, the bottom line is if someone has a solid angle that i'm missing than i welcome it.

Ok that being said. it sounds like your actually mostly agreeing with me.

You do however trail off with more questions. Like

"If the things we perceive as "choices" are "not really choices", then what is really a choice? What do we mean by "choice"? The problem i have is that if you hold a firm position on compatibilism then you should be able to explain it to a laymen by using real proof.

My question to you is how is proof that our "will" is not really controlled by us as ideal conscious agents irrelevant?

It's absolutely relevant.

"free will" then becomes some untestable enity that is open to all kinds of conjecture and speculation. Reason and philosophy but they can only go so far when answering real life questions. So i stack up the data the best i can and make an intelligent decision based on those facts and my own empirical life evidence that i have lived through, but i will stay out of personalizing the problem.

Please just show me a shred of evidence, supporting the fact that we have real control over our subconscious minds in order to make choices freely.

Thanks.

Ok i finally get the etiquette thing of this system. :)

Sorry i am a straight shooter. I will work on my wording, however i still stand by my claims of conjecture vrs facts.

I think of moral questions as those for which there is no good answer. All courses of action and of inaction are bad in a moral question. Often because the possible answers pit the good of the individual against the good of the group, but also pit different groups and their interests against each other.

What do groups have to do with anything? They don't make decisions, people do. If a particular individual is a consequentialist, they should take whichever action is expected to produce the most utility. The truth or usefulness of determinism and free will might influence how we think about assigning moral blame or praise, but they don't tell us what we should do.

There are two false assumptions in the above: 1) that the universe runs on physical laws does not mean it necessarily runs on deterministic laws.

2) Following from that, since laws are not necessarily deterministic, libertarian free will, does not necessarily involve overriding them. Libertarian free will could be found within an indeterministic (but otherwise throughly physical and material) universe.

We cannot just predict what the outcomes of our decisions will be, we really, really have to go through the whole process of making them. We cannot even pretend that decisions are determined until after we have finish making them.

And what about an AI that can predict it's own decisions (because it knows its source code)?

Also, are you a compatibilist?

def DecideWhatToDo(self, environment):
    if environment.IsUnderWater():
        return actions.SELF_DESTRUCT
    else:
        return self.EmergentComplexStochasticDecisionFunction(environment)

int i;
for (i=0; i<5; i++) ;

do_self_analysis();
unsigned long i;
unsigned long j;
for (i=0; i<ULONG_MAX-1; i++)
    for (j=0; j<ULONG_MAX-1; j++);
if(i > 2) return ACTION_DEFECT;
return ACTION_COOPERATE;

Talk about creating a "strawman"!? This has got to be one of the worst articles ever written on the subject of determinism vrs free will. You postulate conjecture more freely than anyone i have ever seen. There is absolutely nothing here to back up your claims, sincerely is this a joke?

You want some scientific proof for Determinism? start with a book called "The Illusion Of Conscious Will" by Wegner. Its a 400 page book that is cover to cover scientific study on the fact that we don't really act freely. Test studies, in Labs!

You are a compatibilist.

And even though i agree the verdict is still out on Hard Determinism. Compatibilism along with free will is just straight up ludicrous. There is no real proof on either and when ever juxtapose-determinism wins over compatibilism every time by a land slide. People that are compatibilist are too smart to concede to having free will alone, but too scared to accept the hard truth that we are not truly in control. They want it both ways and will invent all kinds of ridiculous theories to support their belief.