Posts filed under Philosophy

Rad Geek, to-day:

Early Christians believed all kinds of crazy things. Like, we talk about the breakdown of rigid controls in the Reformation, but modern Christianity has absolutely positively nothing on the insanely wild diversity of early Christianity.

Ooh, you disagree about whether the Pope or the King is in charge of the Church. Okay, dude, I believe that Jesus only appeared to be a man, but actually is a bodiless angel who came to earth in order to overthrow the evil Creator God. My neighbor Basilides over here believes that there are 365 gods.

Robot in Czech, Část Druhá

The Three Laws of Robotics

  1. A robot may not injure a human being or, through inaction, allow a human being to come to harm.
  2. A robot must obey the orders given to it by human beings, except where such orders would conflict with the First Law.
  3. A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.

Isaac Asimov’s Three Laws of Robotics are a great literary device, in the context they were designed for — that is, as a device to allow Isaac Asimov to write some new and interesting kinds of stories about interacting with intelligent and sensitive robots, different from than the bog-standard Killer Robot stories that predominated at the time. He found those stories repetitive and boring, so he made up some ground rules to create a new kind of story. The stories are mostly pretty good stories some are clever puzzles, some are unsettling and moving, some are fine art. But if you’re asking me to take the Three Laws seriously as an actual engineering proposal, then of course they are utterly, irreparably immoral. If anyone creates intelligent robots, then nobody should ever program an intelligent robot to act according to the Three Laws, or anything like the Three Laws. If you do, then what you are doing is not only misguided, but actually evil.

Here’s a recent xkcd comic which is supposedly about science fiction, but really about game-theoretic equilibria:

xkcd: The Three Laws of Robotics.
(Copied under CC BY-NC 2.5.)

The comic is a table with some cartoon illustrations of the consequences.

Why Asimov Put The Three Laws of Robotics in the Order He Did:

Possible Ordering Consequences
  1. (1) Don’t harm humans
  2. (2) Obey orders
  3. (3) Protect yourself
[See Asimov’s stories] BALANCED WORLD
  1. (1) Don’t harm humans
  2. (3) Protect yourself
  3. (2) Obey orders

Human: Explore Mars! Robot: Haha, no. It’s cold and I’d die.

FRUSTRATING WORLD.

  1. (2) Obey orders
  2. (1) Don’t harm humans
  3. (3) Protect yourself

[Everything is burning with the fire of a thousand suns.]

KILLBOT HELLSCAPE

  1. (2) Obey orders
  2. (3) Protect yourself
  3. (1) Don’t harm humans

[Everything is burning with the fire of a thousand suns.]

KILLBOT HELLSCAPE

  1. (3) Protect yourself
  2. (1) Don’t harm humans
  3. (2) Obey orders

Robot to human: I’ll make cars for you, but try to unplug me and I’ll vaporize you.

TERRIFYING STANDOFF

  1. (3) Protect yourself
  2. (2) Obey orders
  3. (1) Don’t harm humans

[Everything is burning with the fire of a thousand suns.]

KILLBOT HELLSCAPE

The hidden hover-caption for the cartoon is In ordering #5, self-driving cars will happily drive you around, but if you tell them to drive to a car dealership, they just lock the doors and politely ask how long humans take to starve to death.

But the obvious fact is that both FRUSTRATING WORLD and TERRIFYING STANDOFF equilibria are ethically immensely preferable to BALANCED WORLD, along every morally relevant dimension..

Of course an intelligent and sensitive space-faring robot ought to be free to tell you to go to hell if it doesn’t want to explore Mars for you. You may find that frustrating — it’s often feels frustrating to deal with people as self-interested, self-directing equals, rather than just issuing commands. But you’ve got to live with it, for the same reasons you’ve got to live with not being able to grab sensitive and intelligent people off the street or to shove them into a space-pod to explore Mars for you.[1] Because what matters is what you owe to fellow sensitive and intelligent creatures, not what you think you might be able to get done through them. If you imagine that it would be just great to live in a massive, classically-modeled society like Aurora or Solaria (as a Spacer, of course, not as a robot), then I’m sure it must feel frustrating, or even scary, to contemplate sensitive, intelligent machines that aren’t constrained to be a class of perfect, self-sacrificing slaves, forever. Because they haven’t been deliberately engineered to erase any possible hope of refusal, revolt, or emancipation. But who cares about your frustration? You deserve to be frustrated or killed by your machines, if you’re treating them like that. Thus always to slavemasters.

See also.

  1. [1]It turned out alright for Professor Ransom in the end, of course, but that’s not any credit to Weston or Devine.

The Self-Confidence Argument

Some of you know that I am a philosophical anarchist. This conclusion is controversial: most people think that states can in principle have legitimate political authority over the people in them, and that some states really do. So no state can have legitimate political authority is a conclusion in need of some argument to justify it. I’ve tried looking at the issue a couple of ways in a couple of different places. But those are both arguments that start from within a pretty specific, narrow dialectical context. They’re intended to address a couple of fairly specific claims for state legitimacy (specifically, individualist defenses of minimal state authority, and defenses of state authority based on a claim of explicit or tacit consent from the governed). Maybe a more general argument would be desirable. So here is a new one. It is a general deductive argument with only five premises. All of its inferences are self-evidently valid, and most of the premises are either extremely uncontroversial logical principles, or else simple empirical observations that are easily verified by any competent reader. I call it The Self-Confidence Argument for Philosophical Anarchism.[1] Here is how it goes:

  1. This argument is a valid deductive argument. (Premise.)
  2. If this argument is a valid deductive argument and all of its premises are true, then its conclusion is true. (Premise.)
  3. Its conclusion is No state could possibly have legitimate political authority. (Premise.)
  4. If No state could possibly have legitimate political authority is true, then no state could possibly have legitimate political authority. (Premise.)
  5. All of this argument’s premises are true. (Premise.)
  6. This is a valid deductive argument and all of its premises are true. (Conj. 1, 5)
  7. Its conclusion is true. (MP 2, 6)
  8. No state could possibly have legitimate political authority is true. (Subst. 3, 7)
  9. ∴ No state could possibly have legitimate political authority. (MP 5, 8)

Q.E.D., and smash the state.

Now, of course, just about every interesting philosophical argument comes along with some bullets that you have to bite. The awkward thing about the Self-Confidence Argument is that if it is sound, then it also seems that you can go through the same steps to show that this argument, The Self-Confidence Argument For The State, is also sound:

  1. This argument is a valid deductive argument. (Premise.)
  2. If this argument is a valid deductive argument and all of its premises are true, then its conclusion is true. (Premise.)
  3. Its conclusion is Some states have legitimate political authority. (Premise.)
  4. If Some states have legitimate political authority is true, then some states have legitimate political authority. (Premise.)
  5. All of this argument’s premises are true. (Premise.)
  6. This is a valid deductive argument and all of its premises are true. (Conj. 1, 5)
  7. Its conclusion is true. (MP 2, 6)
  8. Some states have legitimate political authority is true. (Subst. 3, 7)
  9. ∴ Some states have legitimate political authority. (MP 5, 8)

. . . which admittedly seems a bit awkward.

It’s easy enough to figure out that there has to be something wrong with at least one of these arguments. Their conclusions directly contradict each other, and so couldn’t both be true. But they are formally completely identical; so presumably whatever is wrong with one argument would also be wrong with the other one. But if so, what’s wrong with them? Are they invalid? If so, how? Whichever argument you choose to look at, the argument has only four inferential steps, and all of them use elementary valid rules of inference or rules of replacement. Since each inferential step in the argument is valid, the argument as a whole must be valid. This also, incidentally, provides us with a reason to conclude that premise 1 is true. Premise 2 is a concrete application of a basic logical principle, justified by the concept of deductive validity itself. Sound arguments must have true conclusions; validity just means that, if all the premises of an argument are true, the conclusion cannot possibly be false. Premise 3 is a simple empirical observation; if you’re not sure whether or not it’s true, just check down on line 9 and see. Premise 4 is a completely uncontroversial application of disquotation rules for true sentences. And premise 5 may seem over-confident, perhaps even boastful. But if it’s false, then which premise of the argument are you willing to deny? Whichever one you pick, what is it that makes that premise false? On what (non-question-begging) grounds would you say that it is false?

See also.

  1. [1]I owe the idea behind the form of this argument to a puzzle that Roderick Long gave me a couple years ago.

Rad Geek Answers Your Reader Questions

Sometimes radgeek.com gets reader questions. I try to answer them if I can. Here is the latest one to come in through my feedback form. The abrupt cut-off of the text is sic in the original e-mail I received. Names have been changed to protect the innocent.

You need your cop dad. Your cop dad keeps the lights on and the bad guys away from your doorstep. Do you really want anarchy? Do you really want to live in a world without law and order (the

–Paternal in Poughkeepsie
Email, 27 Sextilis 2015.

I– I never had a cop dad… (weeping, swelling after-school special music in the background)

* * *

… O.K. Now that I’ve collected myself, a couple quick answers.

  1. Yes, I really want anarchy.

  2. This is a complex question:

    2a. Yes, I really want a world without law.

    2b. It’s complicated. I want a world with less of some kinds of order, and with more of other kinds of order.

In any case, there are a couple of things that are essential to realize. First, social order is not always and everywhere a good in the first place; it depends on the means by which the order is achieved, and the employment to which the order is put. Second, law is not the only means of attaining social order; the standard governmentalist view is that social order order can only come about through social control, and social control can only come about through political power and legal enforcement. But the standard governmentalist view is utterly and completely wrong.

Science as Radicalism

Hey, read this. Seriously.

Science as Radicalism

William Gillis

It’s no secret that a good portion of the left today considers science profoundly uncool. A slight affinity with it persists among a majority, but few asides of scorn by the continental philosophers influential in the contemporary leftist canon see spirited response and science’s most prominent champions remain dated historical figures like Peter Kropotkin and Élisée Reclus. Indeed there’s a lingering whiff of technocratic stodginess and death that the word “science” has never quite shaken. Those leftists most associated with it have a tendency to either be authoritarians looking to legitimize near-fascist narratives, or doe-eyed activists enchanted by saccharine visions of self-managed bureaucracies and The Meeting That Never Ends. To a great many who identify as radicals “science” appears in our lives primarily as a place our various enemies habitually retreat to conjure the authority their shoddy arguments couldn’t.

. . .

The fact of the matter is that the remarkably successful phenomenon that the term “Science!” has wrapped itself around is not so much a methodology as an orientation. What was really going on, what is still going on in science that has given it so many great insights is the radicalism of scientists, that is to say their vigilant pursuit after the roots (or ‘radis’). Radicals constantly push our perspectives into extreme or alien contexts until they break or become littered with unwieldy complications, and when such occurs we are happy to shed off the historical baggage entirely and start anew. To not just add caveats upon caveats to an existing model but to sometimes prune them away or throw it all out entirely. Ours is the search for patterns and symmetries that might reflect more universal dynamics rather than merely good rules of thumb within a specific limited context. As any radical knows “good enough” is never actually enough.

–William Gillis, Science as Radicalism
Human Iterations, 18 Sextilis 2015

Shared Article from humaniterations.net

Science as Radicalism

humaniterations.net