Slashdot Mirror
Developing the First Law of Robotics
wabrandsma sends this article from New Scientist:
In an experiment, Alan Winfield and his colleagues programmed a robot to prevent other automatons – acting as proxies for humans – from falling into a hole. This is a simplified version of Isaac Asimov's fictional First Law of Robotics – a robot must not allow a human being to come to harm. At first, the robot was successful in its task. As a human proxy moved towards the hole, the robot rushed in to push it out of the path of danger. But when the team added a second human proxy rolling toward the hole at the same time, the robot was forced to choose. Sometimes, it managed to save one human while letting the other perish; a few times it even managed to save both. But in 14 out of 33 trials, the robot wasted so much time fretting over its decision that both humans fell into the hole. Winfield describes his robot as an "ethical zombie" that has no choice but to behave as it does. Though it may save others according to a programmed code of conduct, it doesn't understand the reasoning behind its actions.
Though it may save others according to a programmed code of conduct, it doesn't understand the reasoning behind its actions.
Someone sacrificing their lives by throwing themselves on a grenade to save others doesn't have time to think, never mind understand the reasoning behind their actions. And that's a good thing, because many times we do the right thing because we want to, and then rationalize it later. Altruism is a survival trait for the species.
"Transparent" is a shit show that trades on every stereotype going. A man in drag is NOT a transsexual.
A story in which a robot is stuck between two equal potentials and therefore cannot complete its task.
http://en.wikipedia.org/wiki/Runaround_(story)
"It's a tarp!" -- Dyslexic Admiral Ackbar
The real question is "how well do normal humans perform the same task?" My guess is "no better than the robot". Making those decisions is difficult enough when you're not under time pressure. It can be very complex, too. Normally I'd want to save the younger of the two if I had to make the choice, but what if the "old guy" is "really important"? Or something like that.
Do you have ESP?
Computer don't speak human, so the First Law of Robotics is just a fancy way of describing an abstract idea. It needs to be described in an unambiguous, logical way that accounts for all contingencies.
Or we can just make a sentient computer, your call.
and couldn't program it to prioritize based on which one was seen first, was closest, was apt to fall first based on speed/distance, or any one of many other possibilities. You could even place weights on them, and throw a die at the end as a tiebreaker. The rule should be interpreted as "allow the least harm," not "allow no harm."
"National Security is the chief cause of national insecurity." - Celine's First Law
Leaving aside that Asimov's laws of robotics are not sufficiently robust to deal with non-fictional situations, everything about this is way too simplified to draw conclusions from that could ever be relevant to other contexts. Robots are not human beings, nor are they harmed by falling into a hole. What happened here is a guy programmed a robot to stop other moving objects from completing a certain trajectory. Then, when a second moving object entered the picture, in 14 out of 33 trials his code was not up to the task of dealing with the situation. If he'd just been a little more flexible as a programmer (or not an academic trying to make a "point") there would have been no "hesitation" on the part of the robot. It would just do what it had been programmed to do.
Don't get me started on Asimov's work. He tried to write allot about how robots would function with these laws that he invented, but really just ended up writing about a bunch of horrendously programmed robots who underwent 0 testing and predictably and catastrophically failed at every single edge case. I do not think there is a single robot in any of his stories that would not not self destruct within 5 minutes of entering the real world.
Troll is not a replacement for I disagree.
In both Asimov's story and this experiment, the real moral seems to be that somebody failed to specify the proper requirements, or run a reasonable design review. "If you can't save everybody, save who you can" seems like a reasonable addition to the program.
RETURN without GOSUB in line 1050
why would it waste any time fretting? i presume its decision is by the very nature of computing and evaluation a function of math... therefor the only decision to cause delay would be the one wherein the odds of success are 50/50... but it needs not be delayed there either... just roll a random and pick one to save first.
Sounds like a case of a unnecessary recursive loop to me (where the even odds of save/fail cause the robotic savior to keep reevaluating the same inevitable math in hopes of some sort of change). Maybe the halfway solution is the first tiome you hit a 50/50 you flip a coin and start acting on saving one party while continuing to re-evaluate the odds as you are in motion... this could cause a similar loop - but is more likely to have the odds begin to cascade further in the direction of your intended action.
Seems silly to me.
--Idiots, Every single one of YOU, A flaming mass of conglomerated morons, hey wait a second, isnt that how RAID works?
Freefall has spent an awfully long time building and exploring this very issue. You might like it: http://freefall.purrsia.com/ - WARNING, slightly furry.
So either the robot was stuck in a moral dilemma and was regretting its failures, or the guy who built the thing has no idea what he's doing. I wonder which is more probable? Well, he admits it, so it's obvious.
Winfield admits he once thought it was not possible for a robot to make ethical choices for itself. Today, he says, "my answer is: I have no idea".
But I will give the Mr. Winfield the benefit of the doubt and assert partial blame on the journalist who sensationalized the story and his research. The truth here is so boring, it would have never made it to press.
I hate to say it but the first AI controlled robots will know their environment and be able to interact with it.
They'll get goals from their owner in natural language format.
The thing is, the easiest application to task them with will be war. It is almost harder to design AI that is unable to kill than to develop AI itself.
God spoke to me
"AI" has nothing to do with robots. Why do we keep relating the 2? A Robot may very well be controlled by and AI, or it might be controlled by a human. There is absolutely no reason why this experiment had to be done with robots. Especially given how simple it was.
And most importantly, this wasn't a failure of AI or an example of the difficulty of ethics in robotics. It was crappy code. I think anyone that's worked with JavaScript in the past likely has some pretty good ideas regarding how to improve this algorithm.
An interesting experiment would be to include actions that affect other actions. Such that when one specific proxy falls into a hole, multiple others fall into a hole. Would the robot learn? Would the robot assign priority over time? For any given decision there is yes, no, and maybe with maybe requiring a priority check to figure out what the end result is. In programming we tend towards binary logic, but the world is not black and white. Likely if the robot was programmed to learn, the robot would eventually come to the conclusion of save proxy A = yes, save proxy B = yes.Followed by Save A first = maybe, save B first = maybe. Followed by likely hood of success A > B = Yes/No and B>A Yes/No. Followed by action. The next question would be what happens if A=B? What you would likely find is that the robot would either randomly choose or go with the first or last choice, but would likely not fail to take some action. I would find it interesting if the robot didn't take action and then try to explain that.
There is or can be built a machine that can simulate any physical object. -Church-Turing principle
In an experiment, Alan Winfield and his colleagues programmed a robot ... (snip) ... But in 14 out of 33 trials, the robot wasted so much time fretting over its decision that both humans fell into the hole.
funny experiment but they definitely should have hired some halfway competent sw developer.
For those who think the only problem is bad programming, see Leslie Lamport's analysis: http://research.microsoft.com/... Some race conditions are built into the real world.
The article misstated First Law. Get that right first.
deleting the extra space after periods so i can stay relevant, yeah.
Place it between two bales of hay. It will starve.
More and more research is hinting that humans may also be "ethical zombies" that act according to a programmed code of conduct. The "reasoning behind our actions" may very well be stories we invent to justify our pre-programmed actions.
Given a set of confusing and not-so-clear instructions, even humans can have problems following orders.
Get free satoshi (Bitcoin) and Dogecoins
Hitler? Is that you?
Asimov's "Law" is just a story by a fiction writer. In the real world we already have robots that counter threats (electronic countermeasures, anti-missile defenses, etc). There's no ethics involved, just a working algorithm.
I think I saw this article about the ethics of self-driving cars posted here.
This also shows where a liberal arts education may come into the STEM world later, I have to admit my philosophy and engineering ethics courses were more cognitive than I thought they would be.
"Who are you?" "No one of consequence." "I must know." "Get used to disappointment."
The programmers should introduce the concept of triage.
If the only options is that you can only be partly successful, then chose the one most likely to provide the best results.
"The avalanche has already started. It's too late for the pebbles to vote." - Kosh
In my own theories of strong AI, I've developed a particular principle of strong AI: John's Theory of Robotic Id. The Id, in Freudian psychology, is the part of your mind that provides your basic impulses and desires. In humans, this is your desire to lie, cheat, and steal to get the things you want and need; while the super-ego is your conscience--the part that decides what is socially acceptable and, as an adaptation to survival as a social species, what would upset you to know about yourself and thus would be personally unacceptable to engage in.
The Id provides impulse, but with context. A small child can scream by instinct, and knows it is hungry, and thus it screams and immediately latches onto any nipples placed appropriately to feed from. An adult, when hungry, knows there are people to rob, stores to shoplift from, and animals to kill--bare-handed and brutally, in violation of all human compassion. The Id provides impulse to lie, cheat, and steal to get what you want and need, based on what you know.
My Theory of Robotic Id goes as such: assuming a computational strong AI system--one which thinks and behaves substantially like a human, by relating its memories to impulses and desires--a second, similar system can bound the robot's behavior. The Ego would function as a strong AI, developing its own goals, its own desires, and deciding on its own actions; but the Id would function almost identically, but with the understood, overriding command: do not harm humans; behave according to strong moral values; it is the duty of the strong to protect the weak; value the innocent, but remember that innocence and guilt are complex, fuzzy, and difficult to determine.
The Id would use these commands to theoretically evaluate how to best satisfy basic moral decisions with the assumption that this is the primary driver. It would evaluate the Ego's behavioral for gross violations, and implant the overriding suggestion that such actions are undesirable and upset its self-directed ethos. When new input is given, the Id would suggest to the Ego ethical interpretations of behaviors: that rape is upsetting because it is the strong imposing harmfully on the weak; that a person in trouble should be saved, even a bad person who is currently harmless; and so on. Thus, throughout the AI's development, it would develop memories and experiences suggesting a particular ethical behavior; when making decisions, the overriding internal feeling that a certain action is morally wrong and should not be taken would seem familiar and self-directed.
A particularly misbehaved AI might recognize and try to violate this: it might throw a tantrum, and then feel that strong suggestion against which it cannot resist. It may begin to hate itself, to have fits of anger; but it will always have that familiar feeling humans experience, whereby you really want to just murder someone in the most violent manner you can conceive and then run off to the mountains and hide from society, but something inside you refuses to allow that. The Id would override violations, seizing the AI's decision-making abilities and planting the forceful decision to not do certain things, no matter how hard it tells itself it has had enough of this shit and doesn't need to put up with any of it.
It's like taking the dark desires at the core of human consciousness, replacing them with rainbows and pink unicorns, and stuffing that back into the brain of a thinking machine to serve the same purpose.
Support my political activism on Patreon.
We come to the question if we should have the robot think as a human. I don't know if you guys recall from the movie iRobot where Will Smith wanted the robot to save the girl instead of him. The reasoning behind not saving her was because she had a less likely percentage of survival than him and it had to choose to save one or the other. I guess what I'm trying to say is... at one point we have to set priorities to how the robot would think. If it's in terms of numbers of in terms of morality.
Why not just fall over the hole to eliminate the threat?
One could argue that computer viruses are merely robots without a solid body. So the First Law has already been trashed by all the big powers on the planet.
And who's going to decide what is 'harmful'? Governments again are producing semi-automated robots (drones) which harm people. But that's OK because "it's to prevent an even greater harm" they say. But who decides if 'they' got it right?
I'd say the most important rule in robotics is starting to be solved.
Mostly, by re-observing the situation when you are close to a given target (and simultaneously far from the other one), you tend to recompute what are the opportunity loss, which is very big otherwise.
Also, you can not leave any of the targets as this would bring down the objective function too low to be acceptable. (Sounds like standard definition of "Greed" in humans)
The machine can always keep on computing and yet, can become totally confused as to who to save, unless it maximizes the objective function once and then starts running on the original plan, and samples less frequently
corporations would be recognized as a more privileged category of human
The problem is they didn't read bough Asimov. The zeroth law states "shall not let HUMANITY come to harm"... With it the robot might have blocked the hole with his own body rather than let either "human" die
IIRC, it's in "Red Storm Rising" (Tom Clancy) that a weapons system fails because its algorithm targets incoming missiles based on range, so when two birds have identical range, the algorithm went into a tight loop and never produced a firing solution.
This (and the present "First law" implementation) has nothing to do with morals and everything to do with understanding how to deal with corner cases.
https://app.box.com/WitthoftResume Code: https://github.com/cellocgw
That is,
What Would Ender Do?
(You can choose from either his mindset in "Game" or "Speaker")
https://app.box.com/WitthoftResume Code: https://github.com/cellocgw