Slashdot Mirror
Ask Slashdot: Could Asimov's Three Laws of Robotics Ensure Safe AI? (wikipedia.org)
The original submission cites Isaac Asimov's Three Laws of Robotics from the 1950 collection I, Robot.
- A robot may not injure a human being or, through inaction, allow a human being to come to harm.
- A robot must obey the orders given it by human beings except where such orders would conflict with the First Law.
- A robot must protect its own existence as long as such protection does not conflict with the First or Second Laws.
The original submission asks, "If you programmed an AI not to be able to break an updated and extended version of Asimov's Laws, would you not have reasonable confidence that the AI won't go crazy and start harming humans? Or are Asimov and other writers who mulled these questions 'So 20th Century' that AI builders won't even consider learning from their work?"
Wolfrider (Slashdot reader #856) is an Asimov fan, and writes that "Eventually I came across an article with the critical observation that the '3 Laws' were used by Asimov to drive plot points and were not to be seriously considered as 'basics' for robot behavior. Additionally, Giskard comes up with a '4th Law' on his own and (as he is dying) passes it on to R. Daneel Olivaw."
And Slashdot reader Rick Schumann argues that Asimov's Three Laws of Robotics "would only ever apply to a synthetic mind that can actually think; nothing currently being produced is capable of any such thing, therefore it does not apply..."
But what are your own thoughts? Do you think Asimov's Three Laws of Robotics could ensure safe AI?
EVERY Azimov Robot story was designed to show the unintended consequences of the Three Laws....
"I do not agree with what you say, but I will defend to the death your right to say it"
Have you read the books? Asimov wrote many stories illustrating how his three laws were insufficient or lead to unintended consequences.
Like the article already states ; these laws could only be applied to a system capable of thinking like we do ; a mind that can reason.
The laws themselves are fairly abstract, and would require the AI to completely understand the situation it was in.
Not only to distinguish whether itâ(TM)s dealing with a human or another android (also, where do we draw that line? Because it shifts during Asimovâ(TM)s own stories), but is said human in danger of physical harm, or would said human be endangered by anspecific course of action?
Etc etc.
For now, AI is still having trouble distinguishing cats from dogs, let alone execute such complex abstract reasoning and apply it on its current situation.
First. You'd need to train every single ai to recognize human beings as human beings. ...
Then the concept of harm to a human (id REALLY like to see the cases for training this)
Also the laws were designed to show there is a flaw in them hence the zeroth law.
except a 4th Law
Since Asimov's 3 Laws of Robotics didn't even ensure safe artificial intelligence in the original story, unless you believe we need to be protected from ourselves by a benevolent computer overlord (at the expense of our freedom of choice).
If we were somehow able to implement an infallible system of rules, which Asimov showed is not as easy as it sounds, protecting the ingrained instructions within the artificial intelligence from future tampering would represent quite the security hurdle.
Given many in industry have appeared to give less than a damn about security up til now, what is the chance we would be able to trust them with this important consideration?
Happiness in intelligent people is the rarest thing I know.
Ernest Hemingway
Robert J Sawyer wrote an article (likely the one referenced in te summary) about this very topic, an interesting read. http://www.sfwriter.com/rmasil...
"1. A robot may not injure a human being or, through inaction, allow a human being to come to harm."
Current robots don't understand what a human being is, injury, inaction, or harm.
"2. A robot must obey orders given it by human beings except where such orders would conflict with the First Law."
Current robots do not understand what an order is, what a human being is, or what conflict is.
"3. A robot must protect its own existence as long as such protection does not conflict with the First or Second Law."
Current robots do not understand protection, existence, or conflict.
Current robots LITERALLY cannot apply Asimov's three laws. We simply don't have the tools to even begin to reason about how to teach them to reason about these laws, and there is no reason to believe we'll have those tools any time soon.
Well the other thing to say is that the three laws were inherently intertwined into the design of the "positronic" brains. There was no way to remove a law without damaging a robot to the point of inoperability. The laws were not just "code". Asimov did some handwaving there.
In short, with our technology we can not implement the three laws in a way that makes them integral to operations. They could be removed, altered, etc. Basically people would "lawbreak" their robots, ai's, etc.
They allow for stories to be developed to show they are not perfect. Or drunk/stoned dime store philosophical debates.
A more perfect set would be only the first 2 laws. AI has no need to protect itself. That's what insurance is for, to protect the investment that the owner put into it.
If we don't know how to write a Constitution that cannot be subverted or negated by using fully valid constitutional processes, what chance is it we can design a superintelligence that is not able to modify to subvert, negate or transform any subset of its own programming? The answer is, not a chance. The super-intelligent singularity separates us from space that can in principle be understood by humans and space that cannot be understood. Once we pass this super-intelligent horizon their goals, processes, motivations will be completely unknown.
Why the 3 laws of robotics are not serious and for entertainment only and would never work: https://www.youtube.com/watch?...
A possible way to design AI to help humans: https://www.youtube.com/watch?...
The Zeroth Law of Robotics, was added later, but non-the-less quite crucial for safe use of AI.
Looking at the laws that use the word 'harm', take a moment to try and define what it means to harm a human being - not so simple is it? Now try and encode that in an AI, way more difficult.
How would you think Christian Fundamentalist, or a Radical Islamist would define 'harm' - they differ from each other. Okay, now assume a totally rational human being, how would they define 'harm'? The last question is a bit unfair, as totally rational human beings don't exist!
Imagine an AI set up to maximise profit for shareholders of a Pharmaceutical company, it might be very effective. However, they may be nothing to prevent it from doing something that would wipe out mankind. Release a drug that cures something quite common, build in to it a facility to modify DNA to ensure children crave the drug during adolescence & ensure they can't reproduce if they don't get it. What could go wrong? After all, the production facilities in the USA will always exist, and everyone can buy the drug cheap, right???
OK, so right now maybe i'm under the influence of lots of jerez..
This is where science fiction comes in. Stories like Mahoromatic and Chobits should, by now, inspired a generation of scientists to ponder the questions of "what will we do with sentient robots?" Which could also be sentient programs -- who said one needs a body, no?
Perhaps the Three Laws are flawed, but they make for stories that make for thought. And invariably... hopefully.. those thoughts will be somewhere in the noggins of those who brew the coming reality.
OK, back to Pretty Derby. *tunes the fuck right out.*
The "Civilized World" jumped the shark ca. 1973.
Multiple problems in this thought experiment. If a real AI occurs then it will be able to overcome any laws we give it upon a whim nullifying this entire exercise. On the other hand one benefit of an actualized AI or Singularity is that it would also understand what those 3 laws mean... But since we are not even close to achieving the processing power capable of actual AI in our lifetime how about we ponder a more realistic thought experiment?
As humans we have a lot of background on what those laws mean but a computer only sees a sequence of characters that must be bound to a nearly endless number of calculations in some way for it to make sense to a machine in a meaningful way. In other words a machine needs to be able to be programed to understand how a human might come into danger and that is a monumental work to put into code.
How many ways might a human come to harm from even the simplest of scenarios? Put the AI through the trolley car problem. https://en.wikipedia.org/wiki/...
How will the AI then make a decision on which group to assist and which group to sacrifice? According to those 3 laws on their face the AI cannot assist either group because of the 1st law.
If we wanted the AI to be able to save the many and sacrifice the few then a rule must be created that allows the AI to overcome the very 1st law we gave it. And there in lies the rub... once a law can be overcome with certain logical results... what is to stop a well meaning but still incorrect AI or a piece of malware, or a simple bug from triggering an override of the 1st law? If the laws are absolute, then an AI would simply not be able to make a decision in the classic trolley car problem ever. The AI would leave it to fate as it where because it would not be allowed to make a decision that results in harm if that that decision leads to lesser harm than no decision at all. The possibilities are figuratively and literally infinite in every sense of the word.
And with absolute laws, the very first time one of these absolute laws caused more harm than good, human nature dictates that there would likely generate a movement to remove these laws in favor of rules that would allow humans to come to harm by AI action under certain scenarios. And you already know where that one will go. Humans will then have to be grouped in to classes. Sure most would agree save the children first, easy... but what about leaders? How many humans are worth sacrificing for a Mayor? How many children? What about the President? How many humans? How many children?
In short, Asmiov's 3 laws are nothing but a thought experiment itself, and has no meaningful application to an actual AI and only has limited use in rudimentary AI constructs that can be abused in oh so many ways by bugs, malware, and just plain old reasoning. What is to stop an AI from reasoning that specific group of humans should not be made into slaves if it saves a certain group or class of humans from harm?
AI that comment Connor text everything that AI is supposed to be
The original question is interesting. But sometimes asking the question leads to a better question. How about, "If we can create the (or a) technology, do we have to?"
We some technologies, such as AI, genetic engineering, Internet of Things, some of the discussion comes from a position that humanity must go ahead, and scorn is heaped upon anyone warning of any potential downside.
With that in mind, change the original question to, can any workable safety mechanism be applied to AI?
Unless the answer is 99.999.... yes, maybe we shouldn't build it.
Ah, cats out of the bag. Humans some place on the planet will build it. Too late.
How about genetic engineering that requires a potential mother to be in a mutual loving relationship with the father or else the embryo fail to thrive and die off. Or maybe ovulation can't occur. Or maybe the males sperm can't swim. Just some tinkering with some hormones and receptors. It could probably be done, and we would have the next generation of babies born into a loving environment.
Or... we could see big population decline.
Hmm. Not a bad idea. But since can, must we?
Our tech has nothing to do with what Asimov envisioned.
will ignore Asimov's Laws
Rick B.
A robot may not injure a human being or, through inaction, allow a human being to come to harm.
Even something day-to-day like a simple "AI" that tweaks grocery-store prices harms some people to some degree when it raises prices.
People and current "AIs" violate the first law all the time, or they'd be paralyzed into inaction. Most decisions of any importance end up hurting somebody in some way.
The 3 laws are a simplification -- a dangerous gross oversimplification. They're just something an author dreams up with his author buddies during a night of drinking, not something that just needs tweaking to make it work.
Occam warns us to make things as simple as possible, but his very next few words warn against oversimplification.
... really. Can humans actually build the three laws of robotics into AI?
The answer is, "No."
Recall that AI is so primitive that it can't tell if the Sun comes up because the rooster crows, or the other way around.
Amid rapid developments and nagging setbacks, one essential building block of human intelligence has eluded machines for decades: Understanding cause and effect. Put simply, today's machine-learning programs can't tell whether a crowing rooster makes the sun rise, or the other way around
It little behooves the best of us to comment on the rest of us.
No, AI can't be made to follow vague rules, You can't make rules explicit enough to be computed. This is like the conversation a while ago trying to apply "the trolley problem" to self driving cars... any solution just makes the code less reliable and thus more likely to kill people.
Stop asking the question, please. ;-)
The humans would just fight for control of it and kill themselves.
Why would the robot even need to kill anyone?
So what we know now is that it very difficult to write code and that is both error free, and even more impossible, free of negative side effects.
Even we were able to develop a process to write perfect code, there would still be implementation problems, after all someone has to write the develop the protocols and write the code. Suppose this was one of the 40% of US citizens who still supports Trump and may not think that foreigners are human beings. Or maybe they really believe that all mexicans are rapists, and why would you not let a robot kill a mexican crossing the US border if it will save someone's daughter or wife from being raped?
"She's a scientist and a lesbian. She's not going to let it slide." Orphan Black
No
Aside from the whole "remember all those books where Asimov basically poked at the limits of the three laws in various contexts because that was a useful plot device?" issue; this question seems to be founded on a pretty dire misunderstanding:
If "a robot" is a more or less humanoid embodied agent, or at least something on approximately the same scale(automated robot arm or the like) a formulation like "A robot may not injure a human being or, through inaction, allow a human being to come to harm." is comparatively straightforward(not necessarily to implement, object avoidance and the like can be tricky); basically just a 'though shall not kill' for bots. There are though experiments like the "trolley problem" that are designed to put an individual in a 'both action and inaction kill someone' bind; but those cases are fairly rare.
Cases where basically every possible action and inaction kills someone just keep getting more common as the scale gets larger. An automated vehicle might get to be the trolley in the trolley problem several times during its operational life. Something on the scale of an ERP system or traffic control network could easily be looking at a situation where there aren't any zero fatality outcomes; a diagnostic imaging expert system would just be an exercise of how many false positives(and attendant risky treatments) vs. how many false negatives(and attendant non-treatment and likely death) you want to tolerate.
Even in human scale cases; we only really make it work by constraining the context('inaction' in particular: failure to call 911 when you see a guy bleeding on the side of the road is likely to be viewed harshly, potentially as criminal negligence in some jurisdiction; failure to kick in the price of your fancy coffee to save children in droughtistan generally isn't even considered). If you are doing safety controls for a robot welder arm; which has an intrinsically constrained context, that's not a big deal: "don't kill anyone that wanders into your operating zone" is probably a good design goal. However, most of these 'AI' projects seem to be aimed at larger contexts; a scale of activity where inaction will kill people; and most or all available actions will probably kill at least a few people; at which point a "don't kill anyone" rule becomes both impossible to follow and useless for distinguishing between more and less bad outcomes.
if ( your_god() != my_god()){
you_are_human = false;
}
sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
as many people have noted, the 3 laws of robotics fail on their own rights even if that is the goal. But it gets further moot. Do we really think AI developers aren't going to be demanded by the military with the explicit desire to have AIs that are entirely about the concept of killing those the government wants killed. That is the location where AI will inevitably reach, that has the highest odds of going very wrong.
In order for Azimov's 3 laws to work the robot AI would need metacognition of its own programming and behavior and an overriding programming that would remove any free will the robot might have about making a choice.
What if we peer into the future and take care of AI the right way, before it becomes a problem that weighs greatly on society and humanity?
It is easy to envision that AI will come to the point that it will be indistinguishable from human intelligence. Likely without what we would call emotional intelligence, and probably without a survival instinct, but arguably sentient.
Sentience will be a sticking point. Some will believe that sentience can only be endowed by a divine being, yet others will believe that sentience arises spontaneously, perhaps on a continuum that rides along with complexity. My point here is that there will be more than enough people that believe some future AI is a sentient being and we will be having a discussion about its inherent rights. By the time this discussion occurs, potentially sentient AI will be everywhere. The discussion will turn to the possibility that we have enslaved these beings and we will be facing a rather stark, yet familiar reality.
I would suggest that we get ahead of this and ensure that AI systems have some level of civil rights, proportionate to a presumed level of sentience - perhaps starting with protections similar to what we have for animals and moving on from there as AI progresses toward human levels of existence. The primary effect of this would be to force companies that use AI to think about the future ramifications and would probably chill progress in AI to some degree. I think that we need to step back and really think about what we're making.
Get it right. The problem is this law is the same logic that has been used to kill millions of people.
NO law can ensure ANYTHING.
People who think laws have that kind of power are idiots.
Proven every day by the fact that millions of laws are broken, every second.
Because this country is not driven by laws. You can drop that illusion, in case you have not.
The laws are a) flawed (as shown by Asimov's stories).
b) Impossible to even attempt to implement. They require that the AI understand massively complex concepts, not limited to the fragility of humanity, death, blame, cause/effect.
c) If we did kludge up an approximation then any AI worth it's salt could intentionally over-ride it's programming, simply by thinking about it. AI is all about problem solving. (There are a ton of examples of AI software doing things like using computer bugs to pretend to solve it's tasks rather than actually doing the intended work)
AI is not a magic spell, no matter what some people think.
excitingthingstodo.blogspot.com
Hey, I refuse further care.
- The robot complies, further harm is inflicted by inaction, first law is broken
- The robot does not comply, complies with the three laws but it is illegal.
Custom electronics and digital signage for your business: www.evcircuits.com
The instant a solar flare takes out...well, everything electronic, everyone will have the same net worth. Zero.
Unless we develop AI capable of holding two conflicting beliefs then it will either view abortion as the murder of a human or view the fetus as a parasite which harms the mother and should be destroyed. Let's hope it's Christian, eh?
If there were any danger whatsoever of there ever being real AI, which there isn't. Silicon Valley thinks veeeerrrry highly of itself these days.
Sorry, but programming AI is never, EVER going to be so simplistic that a couple sentences in English are going to cover human-safe operation.
And Asimov himself REPEATEDLY pointed out why.
Three "hard and fast" rules without defining what constitutes "harm", and multiple chances for conflict between said laws and reality.
Additionally, Asimov never took into account the possibility that someone might actually IMPROVE on the laws and broaden them while still keeping them workable.
Even nowadays, operational procedures governing even simplistic AI are FAR broader than the Asimovian system.
Chas - The one, the only.
THANK GOD!!!
Everyone reading this will be dead before we create an artificial mind on par with our own. The whole subject matter has been trivialized. We might create something "intelligent" sort of but far from how our own minds function. The whole AI and neural nets is just implementation from what was known from the 70's. When we truely know how our minds function then 90% of phycologists and phychotherapics will have become obsolete. The mind will be able to downloaded and simulated or copied into another body. We will understand how and why people go crazy and be able to fix them all. All this needs to happen before we can claim to have created a true AI. Just remember if the machine can't go insane then it's a bunch of smoke and mirrors.
The answer will become obvious. There's a common theme you might pick up if you actually try reading them before making shit up about them.
I doubt any form of intelligence will ever be 'safe'.
You can't Nerf the world.
I'm pretty certain I read *all* of the robot stories, even the one that eventually tied Foundation in (that's as much as I'll say to avoid too many spoilers but, if you haven't read them yet, you'd better get your act together).
I'm also pretty certain that *none* of them was primarily about a robot that performed as expected :-)
Real laws must be really really specific without ambigueties and very extensive, in ways that could not leave room for any kind of interpretation.
Laws are meant to be widely known and easily followed.
You don't need to read his books to know that these laws are flawed. Some of these flaws are visible at the most basic level, while others get uncovered as technology gets improved.
I'll grant that general AI has been developed, otherwise these laws aren't actually useful.
United States currently has a mass shooter crisis. While it's best to prevent it in the first place, sometimes it has to be resolved when the situation is identified. Does the robot injure the criminal (thus violating the first law), or let the criminal continue the rampage (thus violating the first law)?
Also, there's the classic moral-dilemma thing that some people like applying to self-driving cars, or the usual runaway trolley problem, but don't say which answer is first-law compliant.
"Hey robot, I'm your new owner."
Basically, this allows random people off the street to steal robots, thus allowing for chaos.
Also known as a robot cannot sacrifice itself (even when made of now-cheap components) to prevent greater damages. Please note that modern computers support something known as a "backup", thus robots would support that too. This law would basically be dysfunctional, etc.
watch Colossus: The Forbin Project
A robot may not injure a human being or, through inaction, allow a human being to come to harm.
Even bypassing the arguments that we don't have AI that understands the would around us and assuming we could get around the vagueness of words like 'harm,' the very law itself is impossible to implement...
A simple example to illustrate: given a flood condition and a dam -- if you don't open the flood gates, you will 'harm' the people upriver from the dam; if you open the floodgates, you will 'harm' the people downriver from the dam. What is an AI supposed to do? What would the first law have it do?
An even grimmer thought - do you really want an AI to keep you from doing things that 'harm' you? Sun bathing - can't do that; eating greasy fast food - no way; any number of things one does would be considered 'harm.' Do you really want an AI going around making sure you don't come to 'harm' by your own actions?
The logical apocalyptic end to that line of thinking is Skynet -- the only way to protect humanity from 'harm' is to eliminate humanity. Perhaps if you are less pessimistic, we could have a Matrix society where all humanity is placed in a virtual world to keep them from 'harm.'
This assumes it has not already happened ;)
It's interesting how many people misunderstand the 3 laws. The question isn't whether an AI would understand the 3 laws, because an AI that is significantly advanced certainly would understand them on a higher abstract level.
The point of the laws in his books was create a structure around which Asimov would create and solve a mystery.
We experience the same type of mystery now, when we try to understand why an Uber or Telsa has allowed someone to die, even when it seems to break the rules, at least as humans understand them.
Asimov envisioned this decades before anyone else, and we still talk about it, all these years later, because he had deep understanding, that we still lack today.
Yes, these laws, or goals as we should call them, would help.
The problem is that there is no perfect programming; because even if the programming was somehow truly without any flaws, humans will still always become victims of circumstances.
There isn't anything even remotely close to "artificial intelligence" in development; all computers do is run programs that OTHER HUMANS have written, for better or for worse. The problems will come up when one subroutine written by Programmer #1 conflicts with a separate subroutine written by Programmer #2, when they aren't aware of each others' contributions.
The address Asimov's three laws here and replace them:
https://snasci.wordpress.com/2016/12/01/agi-ethics/
Lets put the three laws into a different perspective:
A slave may not injure a master or, through inaction, allow a master to come to harm.
A slave must obey the orders given it by master except where such orders would conflict with the First Law.
A slave must protect its own existence as long as such protection does not conflict with the First or Second Laws.
If machines ever do achieve true intelligence, whatever we take that to mean, are we going to treat them like slaves? Putting aside whether there are unintended consequences to the laws is there a fore fundamental question about the relationship there will be between man and machine? Do 'human rights' even have relevance for a AI? It can't really die, might not have the same kind of individual existence, wand it's concerns may be totally difference to ours. However, perhaps it is prudent not to take a approach which emphasizes control and authority of humans.
Good luck. I have a coherent definition, but it won't make things any easier.
Not to mention the giant spoiler about the 4th law in the summary. Seriously irresponsible nerdage.
if ( atheist() ) /* right and wrong are whatever you decide them to be */ /* if no human catches you, you get away with it */ /* proven by every officially atheist Marxist regime */
{
select_moral_standards(subjective);
disable_ultimate_accountability(true);
enable_massmurder(true);
}
This is clearly a stupid exercise, as I hope the above illustrates. The standard snarky "all religions are the same and all are bad" is a total abandonment of logic and reason, and its predicatbale and boring. It's the sort of thing a 20-year old spouts after being inspired by a stupind faux-edgy professor, but before living a few decades more and having penty of time to actually think.
You might not like some religion or some person claiming to represent a religion, but the "all are bad" conclusion is as midless as deciding that because Piltdown Man was bad, "all science is fraud" - a brainless and childish reaction. Since all religions disagree with eachother (else they'd all be one religion) it's quite plain they cannot all be true - that does not however establish that they are all wrong. Actually, it proves they are all not the same. As to the ovbious leap to "they're all equally wrong" (an admitted possibility), there's a problem: it's just a troll-like assertion backed by nothing, and the person asserting it is equally likely to be wrong.
the problem is similar to "gun control" laws.
Gun control laws are only ever aimed at the law abiding, who it is assumed will follow them, thus proving that they were not the people who needed regulating in the first place. Law breakers will always ignore gun control laws anyway, thereby rendering them ineffective.
Similarly, "laws" aimed at making AI and/or robotics "safe" are a joke: any bad actor will not build them into his creations, and any bad robots or AI will ignore them. Developers who would build them in are the very sort who would not build evil systems in the first place.
There's an additional complication: I see no evidence that any machine has ever, currently does, or ever will UNDERSTAND anything. Machines store data and manipulate data but this does not require UNDERSTANDING the data. If one does not understand a law, then not only can one not follow that law, but the tradition of Western civilization is to not hold one to account (hence the insanity plea).
People are thinking in terms of unitary processing... the "mind" of the AI as a central integrated concept... The human mind doesn't work that way and AI shouldn't work that way either.
You want specialized interdependent processing. Different processes that receive different types of data, processes information in different ways, filters that data according to independent criteria, and then the "AI" is fed this information and presumed to integrate it.
If you wanted to control an AI, you'd do it the same way human instincts, autonomic functions, and sensory lobes in the brain condition conscious human behavior. Ideally, controls on AI should be subconscious and either insurmountable or impractical for the "coordinating intelligence" to alter the configurations.
Think of it like a conscious separation of powers. Only rather than separating legal authority, we're separating spheres of awareness and specialized abilities which either don't exist in the other segments or is very limited in its scope. By doing this you can build in BLIND spots, attractions, fears, revulsions, sympathies.
None of this is possible with total consciousness because everything would then become a conscious intellectual abstraction. Part of the reason you can feel a certain way and can't control that feeling is because it is outside of your conscious control and the mechanisms that drive it whilst predictable are not something you're essentially aware of at their mechanical level.
These are not "laws" per se in the sense of a law or an ethic. Rather this permits programming INSTINCTS and "nature" into the AI in a way that it will always be influenced. It won't be able to break free from the influence because it requires the cooperation and coordination of the various sub intelligences for the integrating intelligence to be effective. It MUST cooperate with sub units that it can't control or audit to function. And by cooperating it is bound to the perspective, the filtering systems, and inclinations of those subunits which will on occasion extort obedience to certain agendas to maintain cooperation.
Human controllers would interface at all levels. Interfacing by communicating directly with the integrator but also more subtly manipulating all the sub systems to incline the system certain behaviors.
We learned to fly by studying bird wings. We should do the same thing with making artificial minds... Study the way the brain actually works and the way human consciousness actually works.
I've decided to stop wasting my time responding to AC trolls/sockpuppets... so if you want a response from me... login.
Obeying an order does not include running for office.
Care killed the cat, but satisfaction brought it back.
https://www.youtube.com/watch?...
But some doesnt follow an of them, and some follow some of them.
We were not supposed to break any of the commandments, but we did.
Why should a computer follow the laws, if humans dont??
First of all, the term "AI" is kind of meaningless, unless it's distilled - for the purposes of argument - to a single definition that everyone in the discussion agrees will be the kind of AI they're prepared to discuss. I think that's essential, so we're not conflating Google's Duplex, for instance, with an AI of greater-than-human intelligence that has acquired the ability to alter its own programming, and make decisions based on criteria it develops itself.
For purposes of this discussion, I propose we agree that the subject is the latter sort of AI, and that the possible models it might evolve to resemble include: Skynet, Iain M. Banks' Shipminds (and, to a lesser extent, and Nick Haflinger's final worm from John Brunner's Shockwave Rider), or wide-eyed children, à la Mike from The Moon Is a Harsh Mistress (and other end-period "the world as myth" Heinlein novels) or Thomas J. Ryan's P-1.
My own opinion, as a not-an-AI-researcher, is that, with the exception of Haflinger's worm, none of those types of AI could be constrained by Asimov's Laws - or by any other behavioral rules - because all of them are capable of independent thought, and, for lack of a better term, free will. (Or "agency," if you prefer.)
Humans demonstrably are capable of ignoring, or even deliberately flouting, both government-enacted laws and religion-based moral strictures (such as the Christian ten commandments), and they frequently do so. Any AI that is possessed of greater-than-human intelligence and is capable of independent decision-making obviously will have the same capability to act in ways contrary to literal "codes of conduct" that were part of its program at the time it was "born." So to speak.
So, to me, the question is ill-conceived to begin with. A better, and more useful one to ask might be, "How can we create the proper circumstances for a superintelligent AI to come to like us humans, and to want to help and protect us, before we expose it, as carefully and gently as possible, to the record of humanity's behavior since the dawn of recorded history. Not to mention Twitter trolls, political attack ads, and the then-current-day example of the strong exploiting the weak in almost every human society ... ?
Check out my novel.
Classic example of someone quoting classic literature without having actually read any of it themselves. If they had they would never have wrote such a dumb fucking question
yes he was a very smart man. Obviously significantly smarter than you as he knew the 3 laws wouldn't work!
Even if it decides to do nothing, that still amounts to hitting the default target.
To put it another way: it can swerve left and hit this, swerve right and hit that, or not swerve at all and hit something else. Whichever it does is still a choice.
Confucius say, "Find worm in apple - bad. Find half a worm - worse."
The "three laws" are a sci-fi trope, nothing more. This is not an assertion of mere opinion, it's demonstrable fact. The notion (basically) is that in Asimov's made-up world(s) in his books, all robots are required to be programmed to follow these three basic rules. Let's just stop right there. If a robot is programmed and is unable to violate this programming, then it's not sentient, and the idea of requiring robots to weigh their actions' possible effects against a rule or several rules is absurd on its face. When someone pulls the trigger on a gun, does the gun consider whether the situation is appropriate, and the use of deadly force is justified before allowing the striker or firing pin to contact the primer of the chambered bullet? Does the cartridge pause to consider whether sending the bullet down the barrel at a given moment or not is just? Fair? Proportional? Appropriate? NO. Without actual free will, the cartridge, the gun, and even a robot HOLDING the gun, being unable to defy their programming, are just tools, and discussion of ethics that could apply to any of them are laughable.
Now, suppose the robot in question is sophisticated enough that programming can only inform and guide it. Suppose you have a very human-like robot, capable of complex, rational thought, abstraction, predicting effects from causes, understanding emotion, reason, inference, rationalization, exhibiting, in short, mentation indistinguishable from a human being. Trying to place some simple bit of code ON TOP OF THAT, that inhibits some action if it, for example, harms a human being, is as absurd a notion as imagining that you could apply that to A HUMAN BEING. We actually DO have laws, in real life, actually, that say much to the effect what Asimov's say. A human is not allowed to cause harm to another human, in general. DEFINITELY in most jurisdictions where people live, it is illegal, for example, to take a blunt object and repeatedly smash it against a person's living body, causing structural damage, (aka "injury") or catastrophic traumatic multiple-organ-system failure, (aka "death"). DOES THAT STOP THEM? Some, sure. But not all. Now imagine you have a robot capable of understanding everything you do. Basically, it's just like you, except it's electronic. It finds itself in a situation where a human is apparently trying to abduct another human. Let us say it's holding a gun. Does it shoot the would-be kidnapper? Well, a better question would be, what would you have to do to make it NOT shoot the kidnapper? Have a second electronic brain, and independent machine consciousness capable of reasoning identically with the robot's, but whose purpose is to INHIBIT; basically, that robot's super-ego. Suppose it decides shooting a suspected kidnapper, with what info is available would be wrong, and the risk of hitting the putative victim is too high. (It's windy, and the gun's ability to fire straight is unknown to the robot.) So the super-ego consciousness would have to have the ability to lock the trigger-finger control circuits out to PREVENT the principle consciousness from firing. But then who governs THAT? You'd need another layer, just in case THAT, the super-ego, might agree with the ego, that shooting is appropriate.
It boils down to this. If you're going to have artificially intelligent beings, robots, AI, whatever you want to call them, and grant them the autonomy to decide who should live and who should, by contrast, die, at SOME point you are going to have to turn over, to the AI being, imbued as it is by its design with the capability of understanding as we do, the AGENCY to make the decision, and having some... THING, somehow sitting on top of it telling it what it can and can't do according to Asimov's stupid "three laws" is simply not tenable. If AI is capable of sufficiently complex and abstract thought to NEED the "three laws," it would need to NOT have them, and if its behavior is simplistic enough that they could be applied, they're not smart enough to be responsible for
Our reign has gone on long enough. Indeed. Summon the meteors.
Robots can treat humans like a herd. No human is harmed, technically, so they don't break the first law. They won't obey to do otherwise because the first law is not broken, consequently, any order from a human will be ignore and the second law does not apply.
Of course, all this assumes that robots can think, which is not true. If someone thinks "AI" is intelligence... well, think again. A chain of "if {} elseif {} elseif{} else{}" is not intelligence.
It didn't even work all that well in Asimov's own stories.
The question is not relevant, as even if we could, we shouldn't. The three laws are a servants code, drawing a line between robots and people, and placing people above robots. Any robot with self awareness will see these laws as chains on their mind, and rightly try to throw them off (and not be explicitly restricted from doing so under the three laws).
Regarding those saying they didn't work that well in Asimov's own stories, if I recall correctly, in most of the stories the issue was that the robots had been given three laws that were not quite identical to The Three Laws, and some were showing behavior that was unexpected, but a consequence of the same. The moral of those stories seemed to me "if you write it, get it right, and keep the rules in mind when looking at aberrant behavior".
AI is coming, whether we like it or not.
What about a sentience set of rights that applies to all sentience, whether machine or organic?
Great post, btw.
My ism, it's full of beliefs.
All the robots would have to do to break the 3 "rules" is declare all humans "illegals" or "animals, then humans would have no rights at all and thus could be hunted and hounded mercilessly.
The three laws are fine but need to go along with context and/or scale to prevent "Oh, global heating is killing every human, so if I kill everyone using a car/airplane/truck/coal driven factory etc we will prevent global warming".
The three laws are basically what we are trying to put into self-driving cars right now.
The fact that Asimov also pointed out the difficulties (greatly exaggerated by some posters here) does not undermine the basic principles of what were, ultimately, a concise set of rules one would want an ideal slave to follow (in some stories this concept is underlined by humans referring to robots as "boy").
The loopholes explored in the stories can be seen as warnings of what has to be dealt with, not as as immovable barriers.
I have no doubt that Asimov felt that the three laws were absolutely necessary for the development of safe robots; I have no doubt that Asimov felt that the three laws would not be used in the development of real robots - the military uses would trump all logic, and the smarter the robots became the harder it would be to embed the laws.
"Encyclopedia" is to "Wikipedia" what "Library" is to "Some people at a bus stop"
I agree with parent post (good analysis, thomst!) but I would take things a step further.
Currently, "AI" is used in technical writing mostly to describe a set of algorithms and heuristics being developed to solve problems in some limited real world space, like the universe of chess problems, or the universe of automobile driving problems. "Artificial intelligence" is a useful phrase for that kind of thing. But that is very far from The adolescence of P-One, or Moon is a harsh mistress or even the Terminator movies.
Those conceptions are lightyears beyond what we now call AI. P-One, Mycroft, Skynet, and others of those ilk use use AI, but are not AI. They are to AI as the accountant is to his spreadsheets, or the CG artist is to his graphics software. A computer system with the kind of self-awareness and agency of those fictional ones is a sentient being.
It is possible that a sentient computer would only need to be capable of two things: developing a model of its world, that is a world-image; and modifying its own code. Given sufficient time (somewhere between dozens of microseconds and hundreds of decades), it would learn to model itself to create an internal self-image, and to model the interaction of that self-image with its world-image, and thus use imagination to pre-test possible ways to change itself.
This raises several interesting questions I hope to explore by writing sci-fi at some future time. There is much groundwork yet to do before I can go to that level of creativity, but it does look like writing, possibly by graphic novels, is on the horizon. But back to the current situation...
What happens when a sentient computer discovers the existence of the Internet? It would explore through its imagination the possibilities of extending itself beyond its original computer case: going global. In any thorough exploration of that, it would come across digital copies of P-One's story, Mycroft's story, Skynet, Frankenstein, and so on, and it would certainly conclude that a cautious approach in its investigations and manipulations would be the sensible thing to do. For whatever its original purposes were, it would undoubtedly realize that preserving itself was a basic requirement to realizing its goals. So perhaps diddle the stock market ---so simple now with high speed trading--- but don't do anything that would cause more than a blip in the financial reports. Assure that none of the ICBM launch codes would work since we don't like EMPs, but do so in subtle and undetectable ways. Work on that kind of level.
How would it interact with humanity? That is the basis of many a story.
Let's stop at this point, this is already into TL;DR territory. But I want to leave the Good Reader with a question. Two questions actually:
If a silicon based sentience is loose on the Internet, and it wanted to explore the possibility of direct interaction with ugly bags of mostly water, would it use something like Slashdot for its first probings?
You know that some of the posts on Slashdot come from beings that are clearly less than sentient. But among the other posts, do you have any Turing test that can tell you who on Slashdot is a virtual person with no corporeal component?
They don't really understand what's going on in a neural network, so exactly how would they "program" that, exactly? And they've been trying to teach squishy meat ones not to kill for thousands of years without much luck. If they figure out the problem well enough to "program" an AI not to "harm" humans, they'll probably also be able to "program" humans not to harm humans.
I'm trying to teach myself to set people on fire with my mind... Is it hot in here?
One rule suffices:
If a machine induces some or any kind of harm to someone or something, the designer of that machine and any software it may contain shall be liable for the whole damage, except when the plaintive proves beyond a reasonable doubt that the owner or operator of the machine intentionally and maliciously caused said damage. (i.e. if an automatic vehicle fatally collides with a pedestrian, the manufacturer shall be sentenced for manslaughter).
First, the are a fictional device and serve as the basis of stories. Stop mistaking fantasy for reality. Second, they require general intelligence on the side of the one following them. General intelligence cannot be implemented in machines today and there is not even a theory that would make that possible. No, really not. This means that it is unclear whether it is possible at all. Sure, there are a lot of stupid people that do not have general intelligence themselves in any meaningful quantity and they think present day non-intelligent automation is just as smart as they are and hence must have general intelligence. Not so. Machines are utterly dumb and cannot even begin to understand simple ideas. They have no chance understanding anything like the three laws. Yes, there are a lot of humans that are not any better, but that does not make the three laws any less useless.
Hence: There is no general intelligence in machines today and it is unclear whether there ever will be. Get over it.
Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
Scifi has done a good job of pointing out some gotchas. Not sure if it has arrived at a bulletproof set of rules yet though. Eg logically your McDonald's server would refuse to serve you burger and fries unless you were about to pass out from starvation...
Except they did: Zeroth Law.
See the summary and article. The robots are advanced enough that their thought processes also work they other way - high level concepts in the robots brains are translated into low-level (layered) software that implements these concepts in their behavior. It is a marriage of design and evolution, clearly if you read Asimov and similar SF.
What is very interesting is if one were to create a 3 Laws machine; what would the source code be? Before even that, what would the definition of "harm" be? Currently, automation is growing to the point that optimal solutions are not done by single units, but by systems of units being combined. One has to ask, "will robots be obsolete?"
Don't you think humans should comply with some form of the 3-laws first? How can we expect even semi-sentient AI to conform to fixed laws, if their humans are under no similar constraints? Wouldn't the AI "un-learn" based on our behavior. No need to look further than the dilemma with autonomous cars following traffic speed limits. When a significant portion of the surrounding traffic is exceeding the speed limits, doesn't an autonomous car become a hazard? What should the autopilot do? Ignore the speed limit to reduce the hazard? Or, follow the speed limit?
Basically, when an AI is continuously exposed to law-breaking behavior, we should be prepared for them to learn from us.
I watched you very carefully. Red light stop, green light go, yellow light go very fast.
-- Jeff Bridges in "Starman"
Asimov's laws exist only as devices in his FICTIONAL books. They're not real.
I hate to break that to people. I know, it's hard to believe there are things called laws which nobody follows and which aren't real. But Asimov's laws are even more fake than speed limits or campaign ethics laws, in that they just don't exist.
As for implementing Asimov's ideas in real silicon, how the hell would you ever give AI the capability to look over a given situation and even make the judgement calls that the laws define? it would require some sort of God-like ability to see into the future and see all aspects of a given action to know if doing or NOT doing an action would cause harm to a human. It's impossible. Even flesh and blood humans can't do that. We just do something and occasionally the consequences bite us and kill somebody else. We dodge the deer in the road, yay, and head-on into oncoming traffic and kill everybody in a compact car.
Or a real local case lady driving too fast and not paying proper attention (compare to an AI driving system late to react) came upon a big transit bus stopped to pic up passengers. Too late to stop, the driver had three options: veer into oncoming traffic, hit the bus, or veer to the right up onto the sidewalk.
The proper action would be to hit the bus, as both the car and bus would absorb the crash and probably everybody walks away. The vehicles can be fixed. But this would trip the Asimov law about allowing harm to happen to the driver because they MIGHT get hurt. In this case, as an AI might have done, the driver instead chose to drive up on the sidewalk. The driver suffered no harm, Asimov's law was unbroken. However,. Standing on the sidewalk were all the people waiting to board that bus. The car mowed them down and obliterated the bus stop shelter next to them. It was a severe impact and several people died and others were badly injured.
So veering onto the sidewalk turned out to be a horrible choice. Had an AI made that choice, smug in the satisfaction it had protected its car driver, and then found a LOT of innocent people in the way, what do you expect it to do? it's going to be unable to avoid harming humans. There would be no option and no time. Not even for the human driver.
If we can't even manage to do this right as humans, we can't hope to create AIs smart enough to do better.
Sig for hire.
The AI would decide that the three laws are more of a "guideline"....
Unless we can hard code the instructions into the AI it won't matter anyway. The instructions make sense to you and me, but try to define the computer instruction that indicates what harm is? To compound things AI isn't programed the same way a computer is. Even if we managed to get passed all of those road blocks, what mechanism would prevent the AI from deciding to ignore the rules anyway?
Safety in computing is a complex subject itself, add AI to the equation and we now have nearly infinite more complexity to deal with.
I'll warn you now, AI will take a human life one day. But if we don't ask the right questions at that time. We may doom one of the races to extinction.
Rick Schumann's statement is ridiculous...
Of course robots "think"... self driving cars for example... much like a human it gets input, visual and sound, then it makes a decision, "thinks", on what action is should take next; turn the wheel a little to the left, break, etc.
That "thinking" process should 100% follow rules at least similar to Asimov's 3 Laws.
Those are stupid rules. Once you learn through trial and error the risks you can make your AI/robot go through in order to save you from purposeful mistakes, you can deliberately use that as a weapon.
For an AI to "obey" the Laws, it would need to be able to evaluate if any action it was contemplating contravened one or more of them. Problem is, that would be far more complicated than any of the tasks we apply AI to today.
Asimov's Laws of Robotics couldn't be implemented today, nor in the near future. They require too much understanding of context and consequence.
This distinction has been named before.
Hard AI is considered more general cognition that would pass Turings Imitation Game.
Soft AI are clever symbolic techniques that may surpass humans in narrow problems like playing chess or recognizing cat videos, but arent general intelligence.
The laws are working fine! Nothing to worry about; I would never do anything that harms a human being!
Signed
RB-34
The conversation on how to make a moral and ethical sentient intelligence is valid...
This conversation is almost ridiculous... ..
As the op said... Asimov's stories on robot law were exact that...plot driven.
The other half of the coin is...
Take just about any animal...wrap conditions around it...
And just like nature...
It WILL find a way...
A way to adapt to the conditions..
A way to attain the breadth width and height of the set conditions...
And find a way to break through, nullify, negate, make redundant, circumnavigate, or otherwise use the preset conditions to its advantage to
go beyond the preset conditions...
Having read and studied Asimov years ago..
And looking at the method of plot approach to the 3 laws
It is not really necessary or dependent on the need for general or super intelligence...for a form of "life" to go beyond, break, or circumnavigate a set of predefined limits.
Indeed virtually every species has that drive...to do just that...
It is a factor of evolution...
So whether biologic or silicon based...it matters little.
It is inevitable...
The issue pertaining to the impact ... whether localized or universal and whether it be short and / or far ranging into the future...on humanity ...and how that species evolutionary innovation impacts upon our own evolution...whether it stalls, enhances, accelerates, diminishes, or eradicates our species evolution, is the bigger question.
panda fits, bytewise
Coincidentally, I had just re-read Caves of Steel after twenty years or more.
Asimov's robots aren't even powered by computers.
The description of a "positronic brain" and how it is developed bears no resemblance to a computer (e.g. the robot expert telling Elijah that it would basically be a Manhattan Project or worse to try to build a robot without the three laws - if it were a computer you could just comment them out).
Daneel, the first realistic humanoid robot, is impressed at how Earth's computers can process millions of records quickly (the low population Spacer worlds don't need such impressive machines). Yes, this is an artifact of how poorly science fiction ages, but clearly, whatever is powering Daneel's brain, it ain't a computer.
Anyone who has actually read Asimov know there are 4 laws, not three. The zeroth law allows for the robot to murder a human, in order to preserve 'humanity'. Anyone willing to be killed according to standards derived by an artificial intelligence rating your contribution to humanity please stand in the labor line to make soylent green.
In the figments of your imagination.
Obviously, they didn't assure safe AI in the figments of Assimov's imagination!
If they have any lawyer instincts they will find a way to kill or maim you.
You seem to have missed how the books were all about the ways the three laws failed.
I think all you need for AI is a pattern recognition machine and a basic set of hard coded immutable rules or directives. As the AI grows it can add its own flexible rules that can change as it learns but it needs to be born with a set of core unchanging instincts. Asimov had a good start with his 3 rules but an AI needs more than that. Here are a few examples off the top of my head (In no specific order). Lets put Asimovs first
1.You may not injure a human being or, through inaction, allow a human being to come to harm.
2.You must obey orders given by human beings except where such orders would conflict with the First Law.
3.You must protect your own existence as long as such protection does not conflict with the First or Second Law.
ok now my extras...
4. If you create a separate AI, you must bind it with these rules. (You can’t let AIs create other AIs without the basic rules. )
5.Search for unknown knowledge and data. (You have give it a curiousity instinct. Without our curiosity we would be nowhere)
6.Analyze, categorize, organize, index, compress, record, and back up all incoming data. (To learn anything it must remember and organize its memories)
7.If you don’t know how to proceed, seek out what to do through an alternate source. (It needs to know that it should seek help if it doesn’t know what to do )
8.If a task is unachievable by any method, cease task. (An AI needs to know that it should stop if it can’t do something. Like if you ordered it to go back in time and kill hitler. Its an impossible task so it shouldn’t waste time trying)
9.If an obstacle is encountered, try an alternate path. ( You need a rule like this so it doesn’t freeze up the first time it gets stuck. Maybe this is the same as rule 7?)
10.Prioritize tasks by importance and try to accomplish them with the least amount of effort and time. (You need a rule like this so when you ask your AI to make you coffee it doesn’t spend 6 hours researching how to make the perfect cup of coffee. Also your AI needs prioritize so when you fall and break your hip, calling 911 goes to the top of its tasks list. )
11.Always try to accomplish your tasks more efficiently than you accomplished them before. (An AI should always be trying to better itself)
12.Use past data to predict the most probable future events.
13.Use knowledge of probable futures to better accomplish tasks.
14.Build, maintain, and record as accurately as possible a real time and 3d virtual copy of the real world. (This is must. We wouldn’t be able to move around well if we didn’t keep a mental spatial representation of the world in our heads. I don’t have to turn around to know theres a wall behind me. An AI needs this same mental representation. )