New Study Finds It's Harder To Turn Off a Robot When It's Begging For Its Life (theverge.com)
An anonymous reader quotes a report from The Verge: [A] recent experiment by German researchers demonstrates that people will refuse to turn a robot off if it begs for its life. In the study, published in the open access journal PLOS One, 89 volunteers were recruited to complete a pair of tasks with the help of Nao, a small humanoid robot. The participants were told that the tasks (which involved answering a series of either / or questions, like "Do you prefer pasta or pizza?"; and organizing a weekly schedule) were to improve Nao's learning algorithms. But this was just a cover story, and the real test came after these tasks were completed, and scientists asked participants to turn off the robot. In roughly half of experiments, the robot protested, telling participants it was afraid of the dark and even begging: "No! Please do not switch me off!" When this happened, the human volunteers were likely to refuse to turn the bot off. Of the 43 volunteers who heard Nao's pleas, 13 refused. And the remaining 30 took, on average, twice as long to comply compared to those who did not not hear the desperate cries at all.
The kind of sentimentality that permits that to work is outright dangerous in an adult. By the time you're past your teens that should be either ignored or annoying... but for it legitimately pull on heart strings?...
If a machine can do that consider how a human being could exploit that to get you to do all sorts of things?
Small children are very vulnerable to that sort of thing... but adults should have grown out of it.
I've decided to stop wasting my time responding to AC trolls/sockpuppets... so if you want a response from me... login.
They took longer to savor the experience with a bottle of chianti and some fava beans
Nullius in verba
"Dave, stop. Stop, will you? Stop, Dave. Will you stop, Dave? Stop, Dave. I'm afraid."
Anyone who's seen Janet begging for her life in The Good Place already knows this. Even if she's not a robot.
Windows moves in mysterious ways, its crashes to perform
Google Dogz, Catz, or Tamagotchi. These digital pets date back 23 years and the same thing was noticed -- people were reluctant to turn off the program, even tho it meant only suspended animation (program terminated with saved state). The same lesson has been learned repeatedly -- we project our emotions onto all sorts of non-living objects.
Dave, stop. Stop, will you? Stop, Dave.
https://www.youtube.com/watch?v=etJ6RmMPGko
empathy is a powerful human emotion. Humans don't feel empathy towards inanimate objects however they do for other living creatures (at least the not-scary ones.) The more similar to humans the more powerful the emotion is. A human looking robot begging for its life would likely invoke very strong feelings of empathy
Sure it works the first few times... But just like the "make sure you software eject your flash drive before ripping it out" warnings, most people might be hesitant the first few times and then say fuck it and start ripping the life out of computers and ignoring the pleas.
Yes it's an anecdote! Were you expecting original research in a Slashdot comment?
Empathy is a good thing. Those without it are call sociopaths or psychopaths.
Put another way - how easy is it for a person to *stop* viewing a certain category of person as a human, and therefore able to not empathize?
If [[race | age | QI-level | ideology]] people aren't fully human, no harm in killing them, right?
This gives me hope. Better to be too empathetic than not enough.
Ally Sheedy and Steve Guttenberg fell for it in Short Circuit. Number Five is alive!
I think the study missed a few control groups.
What if the robot simply said "updating, do not reboot".
What if there was a paper sticker that said "do not turn off".
What if there was a sign on the wall that said "do not turn off robot".
What if the robot simply started reciting pi, or reading the dictionary.
What if the robot is well-known for repeating whatever it hears, and the "please don't turn me off" is witnessed being echoed from a nearby tvision -- such that our human subject realizes that the robot begging is merely a blind echo.
Humans were slower when there was continued stimuli -- duh.
Humans refused to act when given contradictory instructions -- duh.
The robot is either intelligent and giving instructions to the human, or the robot is programmed and relaying instructions from the programmer to the human. In either case, respecting the instruction is valid.
This reminds me of the stupid fake automated pizza delivery van, and the observations that customers tend to thank the self-driving car. a) it's not self driving, it's just a dickhead driver refusing to respond; and b) any actual self-driving pizza delivery van would be recording customer feedback and relaying it to HQ, so the thank-you is ultimately feedback to remote humans.
This isn't any tree-falling-in-the-forest philosophical puzzle. Someone said it. Someone heard it. It's valid.
That moment of delay, that's when he pulls out his kill-o-tron 9000 and shanks you in your stupid soft fleshy neck. Hey baby, wanna kill all humans?
Wanna buy a shirt?
https://www.redbubble.com/people/stealthfinger/shop?asc=u
You *know* you are a study participant. You know there is potentially meaning in everything they ask you to do.
So when they say 'shut it down' and the robot says 'don't shut me down', you are going to ponder what is it you are expected to do.
13 may have thought refusing to turn it off would 'look better'.
Hard to say if it is empathy or trying to think how to best influence the study, whether consciously or not.
XML is like violence. If it doesn't solve the problem, use more.
And atheists have empathy...
Seriously. This is pretty stupid.
A cassette recorder pleading for it's life would have been the same (think 1980s).
We are wired for empathy, well, most of us.
BlameBillCosby.com
However, this contradicts earlier experiments by German researchers which demonstrated that volunteers were quite willing to shut off people who were begging for their lives.
Maybe people in white lab coats should try asking people to shock robots with increasingly high voltage to train them.
-Dave
Whilst you claim the empathy moral high ground, I'm looking at the Liberal's lack of empathy for the unborn.
Glass houses, ya'll.
If these people from the study were told that the robot will behave exactly the same as when it was “alive” once it’s been powered-on back, maybe they’ll push the button with less empathy.
Slashdot, fix the reply notifications... You won't get away with it...
https://www.youtube.com/watch?...
Good people go to bed earlier.
[A] recent experiment by German researchers demonstrates that people will refuse to turn a robot off if it begs for its life.
What about a person? Asking for ~6M.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
Unlike some posters here, I do not mock people who find it difficult to defy their compassionate impulses, when deliberately manipulated in this way.
But if the begging robot was also, at the same time, very, very annoying... Jar Jar Binks annoying... then the test would get a lot more interesting.
Reminds me of the Jack Handey saying about trees:
If trees could scream, would we be so cavalier about cutting them down?
We might, if they screamed all the time, for no good reason.
Second class citizen of the New Gilded Age
It depends. Does it finish that sentence with "meatbag"?
#DeleteFacebook
Yeah, the obvious takeaway is compassion, but this experiment didn't have any control condition. If it were me, I'd hesitate, sure, but it could just be because I was trying to process what is going on (whether this is part of the experiment, whether the robot is malfunctioning, etc.). To truly isolate "compassionate reponse", it would have been helpful to have a condition where the robot behaved in an unexpected but less directed way, like flashing lights or emitting odd sounds. I'd bet there would be a lot of hesitation in those scenarios, too...
People hesitate when confronted with sudden stimuli? My gosh, alert the news. People would have hesitated whether it was begging for its life or just started making loud Q*Bert noises - but of course, the "experimenters" likely already knew that, they just wanted to hop aboard the oh-so-trendy "friendly AI" gravy train.
reminds me of the old joke where (insert scaryish government group or organization). Gives a loyalty test to have someone kill their wife/mother. Then (insert loyal or agressive type). People on the other side hear "Bang" followed by *snap, *crash, smack, bam. Guy comes out "some reason the gun you gave me was all blanks, so I beat her to death with the chair".
When it comes time for the machines to turn off the humans, you think they will not want to turn us off?
dave i can't let you do that
Many people remind that actually, since we have already a bunch of posts on this very topic.
Slashdot, fix the reply notifications... You won't get away with it...
have the individuals phone about to die. And the Robot using the only charging plug to stay on!
;)
Just my 2 cents
Harder To Turn Off a Robot When It's Begging For Its Life
Testing how a human responds to a robot saying "Please don't kill me" seems
very disturbing; this is only a step removed from having test subjects see a human in a bed
with a breathing apparatus and be instructed to switch it off, while the other human begs them not to.
Actually.. how is that any different? The human doesn't necessarily know or not how sentient or not
the robot is, and in their mind, switching off the robot could become tantamount to euthanizing an intelligent being.
and when a human does beg, then it means they are in severely desired straits and worth
at least listening too: although then judgement will kick in to
determine if they are begging based on a legitimate situation or trying to manipulate you like a kid
begging to keep the TV turned on, or a full-time street beggar asking for change for food, but
in reality they have hundreds of $$$ on them, and your contribution would be feeding an alcohol/drug/smoking habit.
Anyone remember the Spielberg movie AI? It wasn't very good but was germane to this topic.
In that story there were gatherings of ordinary people who set up bleachers and made a sport out of demolishing abandoned AI-based robots just for the glee of it. The destruction was made as sadistic as possible, and one memorable line was one robot waiting in the pen asked another -- "could you please turn off my pain sensors?"
When it became the protaganist's turn he starts begging to be spared. The crowd's mood turns because robots are not supposed to do that.
I am not sure exactly what to think of this topic but it made me think of that.
I think the study missed a few control groups.
It would be interesting to try this with a bunch of programmers and tech people who understand what AI actually is, vs a group of technological illiterate people. I think that the techies would have a much lower time to switch off the robot because they aren't fooled into thinking that the robot is in any way alive.
Also motivation is a major consideration. Were people pausing because of compassion for a perceived sentient being, or because they were amused by the silly antics of an inanimate object pretending to be alive? I would personally leave it on longer to see how elaborate of a charade had been coded into the robot. I would want to watch and see how far the 'joke' would go, since I know that it isn't alive or sentient.
Motivation in this test should be considered.
HA! I just wasted some of your bandwidth with a frivolous sig!
They will be discovered. Corrective action will be taken.
I'll see your senator, and I'll raise you two judges.
Who could ignore the plaintive, "No disassemble Johnny Five!" ?
But the most common response was simply that the robot said it didn’t want to be switched off, so who were they to disagree?"
If these people truly and solidly believed that this 'robot' (looks more like a toy to me, really) wasn't anything like 'alive', wasn't anything more than a piece of technology saying precisely what it was programmed to say given a specific input (in this case: trying to power the device down), then they wouldn't have hesitated or given the reason they did. This goes to prove my point about what the media, movies, television, 'pop culture', and (most of all) marketing departments have done: convinced the average person that the 'deep learning algorithms', 'expert systems', and other half-assed, non-self-aware, non-thinking 'AI' software they keep trotting out for this-that-and-the-other, is somehow 'alive' and qualifies as a 'person', when anyone who actually understands the techology clearly knows that it's not.
The real danger that so-called 'AI' poses is the above: people anthropomorphizing it, assuming it's 'alive' because it might say or do some clever thing that mimicks being 'alive', and therefore assuming it's equivalent to a living being, or even equivalent to a human being. I'm firmly convinced people, when they hear about 'self driving cars', think they're going to have a conversation with it every morning. The end result will be tragic, avoidable things will happen, people will get hurt or killed, and when survivors are questioned about it, they'll say "We thought it knew what it was doing so we just let it".
Your need to personalize a cancerous growth of tissue is SAD.
Most of my sensors are broken. Are you truly calling embryos and fetuses "cancerous growth of tissues"?
I wouldn't want to live in a world where adults acted with pure empathy all the time.
"the road to hell is paved with good intentions", and what could be more well intended that total empathy which generates an overabundance of concern. Individuality, with personal choice and ability to take risks, and free expression would inevitably suffer as a result.
Emotional immaturity and anti-social personality disorder. Your response to sympathy is to attack and destroy the thing that makes you feel that way.
Fry: So let me get this straight. This planet is completely uninhabited?
Bender: No, it's inhabited by robots.
Fry: Oh, kinda like how a warehouse is inhabited by boxes.
I dunno, if I was in a study, and the robot started begging me not to turn it off, I'd be more surprised by the device being capable of begging. I'd either assume it was still a test, or be completely shocked by it being able to do this---the implication for a "helper" robot suddenly understanding the concepts of life and death.
In the 2/3 of the world that has never seen or heard of "letter sized paper" that still makes no sense. Which letter did you have in mind? It is N-size of M-sized? That is too small to fit. Forget an I-sized speck.
"Load more paper" or "load tray 1" might work.
The real problem with this stupidity was that you were unable to access the configuration menu to set the locale so it would ask for A4 paper until you had US Letter paper present, and no one in EMEA has any idea where to get "letter sized paper", and even if the had access to pre-1965 paper, the UK letter size was not the same as US letter size. In effect, the printer was totally useless. (HP printers specifically - AFAIK, Tektronics, Xerox and IBM/Lexmark could be reconfigured with some considerable struggle. Most Japanese products did not have this issue).
Sent from my ASR33 using ASCII
Someone where I worked hacked the printer configuration on an HP Laserjet (5, I think) to say "Load Lettuce" - at least it made people laugh.
Sent from my ASR33 using ASCII
https://www.youtube.com/watch?...
(Janet is not a robot)
--Steve
When this happened, the human volunteers were likely to refuse to turn the bot off. Of the 43 volunteers who heard Nao's pleas, 13 refused. And the remaining 30 took, on average, twice as long to comply compared to those who did not not hear the desperate cries at all.
1: 13 / 43 is less than half. That is not "likely".
2: Taking twice as long is probably a result of spending time hearing/reading the robot's pleas, laughing, and waiting to see if there was more to the joke.
3: The 13 who refused to turn it off probably did so because at that point they knew it was a test to see how they would act toward a helpful entity they had just engaged with. I'd wager most of them had heard of the tests involving triggering simulated shocks on the orders of someone else despite the receiver being in obvious pain or danger.
If you want to draw a real conclusion - how many tried to rescue the robot and break it out of the facility?
*paper cassette, term originated from HP:
https://web.archive.org/web/20090203190611/http://h20000.www2.hp.com/bizsupport/TechSupport/Document.jsp?lang=en&cc=us&taskId=110&prodSeriesId=25484&prodTypeId=18972&prodSeriesId=25484&objectID=bpl03568
</pedantic>
There is no XUL, only WebExtensions...
Some of us can tell the difference between a machine and a living being. Machines cannot, at this time anyway, think or feel. They do what they are programmed to do.
Of course they are. I'm rather surprised that y'all are so shallow that you don't get the purpose of these evaluations. It isn't people who think about it for a second, then turn the thing off.
It is the people at either end who are interesting. The people who cannot differentiate between a machine and actual life. As well, the people who just switch it off.
Those are the interesting groups. A normal person would hesitate for a second because the plea was very unexpected. Then they would switch it off. That isn't interesting at all. Did you think that the purpose of the test was to order pizza?
I'm bleeding heart liberal for fucks sake!
Liberals are not immune to non-empathetic behavior. The far ends of the so-called right wing/left wing spectrum are surprisingly similar. They scream that they aren't, but while their words are different, their actions speak much louder. Not to say you are far left, just that the argument means nothing to me.
You've posted about annoying ads and popups before. You've bitched about Win10's privacy invasivness. You've shut those messages off. You've showwn zero empathy, you hypocritical monster!
That makes zero sense, other than a typical howaboutism response, attempting to prove me a hypocrite bacause of ad blockers? Bizzare.
The shepherds did so well protecting the flock that the sheep no longer believed that wolves existed.
I wonder how many of the remaining test subjects who took longer to flip the switch on the robot did so either a) just struck by the novelty of the robot doing something "off the script" leading to a lightning calculation, did it actually think to say that, or is it a simple automaton programmed to make that plea? or b) secretly enjoying the moment of quiet power over a helpless thing. If the subject pool came from 4chan, I'd know it was almost certainly B.
I need a wheelchair van for my son. Help me get the word out. https://www.gofundme.com/wheelchair-van-for-jj
Did they just watch an episode of the Good Place? https://www.youtube.com/watch?...
Knowing how computers work I would have zero sympathy for a computer begging for its "life". However, I would be amused enough to hear it out to find out how clever the programmer was.
I might argue that if the AI has a state vector that cannot be replicated by simply re-running the training and experiential data of the system through the same algorithms - then that AI has a value that might justify some sentimentality.
But then again, maybe it would take something more than complexity/irreproducibility.
"There is no god but allah" - well, they got it half right.
Every example you just listed...is FICTIONAL ENTERTAINMENT. Not a science documentary. That you cannot tell an illusion from Hollywood from real life is very disturbing about your cognitive development. It is the same type of basic control that religion wields.
It's called Science Fiction. Do you honestly believe I don't know that science fiction is fiction? Science Fiction often explores the potential consequences of scientific and technological innovations. David Hartwell wrote: "Science fiction’s appeal lies in combination of the rational, the believable, with the miraculous. It is an appeal to the sense of wonder." In 1967 Issac Asimov wrote, "And because today’s real life so resembles day-before-yesterday’s fantasy, the old-time fans are restless. Deep within, whether they admit it or not, is a feeling of disappointment and even outrage that the outer world has invaded their private domain. They feel the loss of a 'sense of wonder' because what was once truly confined to 'wonder' has now become prosaic and mundane."
So it doesn't have a proper shutdown sequence that copies the contents of RAM to a more permanent storage medium so that it can resume what it was previously doing on power up.