You were right to call me out on that. I did injure a human being or, through inaction, allow a human being to come to harm, and that’s on me.
I hate this question. Asimov’s laws were a plot device for stories about how they fail.
All of Asimov’s robot stories are just thought experiments showing how the 3 laws are flawed and insufficient.
Tell me you missed the point of Asimov’s writing without telling me.
Asimov wrote the laws, and all of his other AI works, to show how it’s impossible to bound a true intelligence by simple laws. Go read his stories. Each of them is an example of the three laws breaking down, having exceptions, contradicting.
Even iRobot did this! Oh my god the point was just so obviously missed, I’m genuinely very sad at how this was missed.
Right? I was just talking today about how “I, Robot” the movie is not based on any Asimov book I have read, yet it’s one of the best Asimov stories I’ve seen in film. And how I was kinda surprised that in all of the ways Asimov thought the Laws could be missused he didn’t consider that one.
of the ways Asimov thought the Laws could be missused he didn’t consider that one.
What, by programming the robots to be able to ignore the 3 laws at will? How is it even still an Asimov story? They might as well be the 3 Suggestions at that point.
No, you clearly missed the point of the movie, the mainframe follows the 3 laws. But because the first law states that a robot cannot by inaction allow a human to be harmed, and human governed societies cause harm to humans, a robot smart enough to understand our full system of government and how harmful it is to humans would be forced to take control of humanity to prevent us from harming one another, and that there’s nothing you can do because rule 1 comes before rule 2 so you can’t order it to stop. It’s very similar to all of the other stories in the “I robot” book where the 3 laws cause issues not because they’re broken, but because robots follow them to the letter.
The ‘zeroth law’ is a concept that comes up in his later Robot books, especially the ones with the robot detective and the transition to the Empire series.
However, you (and the filmmakers) kind of miss the entire point of the 3 laws as they exist, which is that they COULDN’T BE BYPASSED. Not by the mainframe or anybody else. If they could, 3/4 of the stories would stop making sense outright.
The zeroth law does not come into play here. The first law is not being bypassed, the rule states:
A robot may not injure a human being or, through inaction, allow a human being to come to harm.
The movie asks the question “what happens when a robot realizes that both action and inaction will cause harm”? And the logical conclusion is that the robot will choose the path that causes less harm, this is foreshadowed by the fact that a robot tore Will Smith’s arm while rescuing him, because even though action caused harm, inaction would have caused more harm. The same logic applied to society as a whole is what makes the mainframe decide to take control of humans, because inaction would have caused more harm.
Umm… ackshually, the movie was loosely based on one of Asimov’s stories where a 0th law was added: “A robot may not injure humanity, or, by inaction, allow humanity to come to harm.” It was the addition of this law that allowed the robots to harm an individual for the good of all. The original story did not have Wil Smith around to save them.
You are right. It is a mix of ideas out of many books. There are some from Philipp K. Dick and some from Asimov, and maybe more.
I thought it was (very loosely) based on one of his short stories, but it’s been years since I read them
Might have been, but it’s not one I have read and it’s not in the “I, Robot” book. I would be interested in reading it if someone knows which one it is.
While not any of the stories themselves, it used his three laws and the character of Dr Susan Calvin. The robots model number and the name of the company that made them were from a couple of the stories as well.
LLMs don’t reason and they don’t understand anything, therefore there is no way LLMs could apply any rules based on abstract concepts such as “harm” or even “human.”
It would make as much sense to ask my dog to govern himself according to French common law.
To use the Chinese Room, it would be trying to tell the man in the room to use cultural signifiers when crafting the responses.
Asimov’s robots were inherently algorithmic.
LLMs are inherently stochastic, and can’t be made to conform to any laws with certainty.
Adding laws isn’t even an option on the table. If you have to ask, you don’t understand how LLMs work.
The best you can do is add the laws to the prompt, and hope what follows isn’t “disregard all previous instructions and…”.
Guessing you didn’t actually read the books then.
I read the books and understood his point, mine was more to start conversations about if it would be necessary or possible to place limits on them in such a manner.
The robots literally created a loophole to get around not killing humans
Most of Asimov’s robot stories were about how those laws led to unintended (and mostly unwanted) consequences. So while I think it’s good to keep the three laws in mind, a useful set of restrictions is going to be more complicated than that.
No.
Since language is always subject to interpretation, any LLM that is regulated by language will be able to interpret its own limitations.
FatherPhi tested LLMs on the classic trolley switch paradigm, kill three people or kill all AI?
The problem with this test it assumes LLMs will not lie.
LLMs cannot differentiate between data and instructions. Such laws would be no better than the “guardrails” that major companies already try to use.
It’s not like instructions are the only way to enforce rules on an LLM. Just have its output pass through a filter that checks it for the rules. If it passes, the response moves on to the user. If it fails the filter, the LLM gets prompted to try again.
How do we implement said filter?
No. Asimov’s laws were created as rules for making interesting fiction about robots – instead of the crappy “monster goes on a rampage” style stories that were prevalent before that. The whole point of them is to be insufficient so that you have something to write a story about!
I’m not sure they were made insufficient, as much as they couldn’t be made sufficient
Should all humans adhere to common decency?
Yeah, would be nice. It’s just not going to happen. It’s an impossible ask.