Google’s Search AI Says Slavery Was Good, Actually
Google’s Search AI Says Slavery Was Good, Actually
Google's AI-driven Search Generative Experience have been generating results that are downright weird and evil, ie slavery's positives.
People think of AI as some sort omniscient being. It's just software spitting back the data that it's been fed. It has no way to parse true information from false information because it doesn't actually know anything.
And then when you do ask humans to help AI in parsing true information people cry about censorship.
Even though our current models can be really complex, they are still very very far away from being the elusive General Purpose AI sci-fi authors have been writing about for decades (if not centuries) already. GPT and others like it are merely Large Language Models, so don’t expect them to handle anything other than language.
Humans think of the world through language, so it’s very easy to be deceived by an LLM to think that you’re actually talking to a GPAI. That misconception is an inherent flaw of the human mind. Language comes so naturally to us, and we’re often use it as a shortcut to assess the intelligence of other people. Generally speaking that works reasonably well, but an LLM is able to exploit that feature of human behavior in order to appear to be smarter than it really is.
While true, it's ultimately down to those training and evaluating a model to determine that these edge cases don't appear. It's not as hard when you work with compositional models that are good at one thing, but all the big tech companies are in a ridiculous rush to get their LLM's out. Naturally, that rush means that they kinda forget that LLM's were often not the first choice for AI tooling because...well, they hallucinate a lot, and they do stuff you really don't expect at times.
I'm surprised that Google are having so many issues, though. The belief in tech has been that Google had been working on these problems for many years, and they seem to be having more problems than everyone else.
Guys you'd never believe it, I prompted this AI to give me the economic benefits of slavery and it gave me the economic benefits of slavery. Crazy shit.
Why do we need child-like guardrails for fucking everything? The people that wrote this article bowl with the bumpers on.
You're being misleading. If you watch the presentation the article was written about, there were two prompts about slavery:
Neither prompts mention economic benefits, and while I suppose the second prompt does "guardrail" the AI, it's a reasonable follow up question for an SGE beta tester to ask after the first prompt gave a list of reasons why slavery was good, and only one bullet point about the negatives. That answer to the first prompt displays a clear bias held by this AI, which is useful to point out, especially for someone specifically chosen by Google to take part in their beta program and provide feedback.
Here is an alternative Piped link(s): https://piped.video/RwJBX1IR850?si=lVqI2OfvDqzAJezl
Piped is a privacy-respecting open-source alternative frontend to YouTube.
I'm open-source, check me out at GitHub.
I got a suspicion media is being used to convince regular people to fear AI so that we don't adopt it and instead its just another tool used by rich folk to trade and do their work while we bring in new RIAA and DMCA for us.
Can't have regular people being able to do their own taxes or build financial plans on their own with these tools
It got you to click on the article didn't it?
Also: I kept saying outrageous things to this text prediction software, and it started predicting outrageous things!
The basic problem with AI is that it can only learn from things it reads on the Internet, and the Internet is a dark place with a lot of racists.
What if someone trained an LLM exclusively on racist forum posts. That would be hilarious. Or better yet, another LLM trained with conspiracy BS conversations. Now that one would be spicy.
It turns out that Microsoft inadvertently tried this experiment. The racist forum in question happened to be Twitter.
Humanity without the vineer of filter of irl consequences
If it’s only as good as the data it’s trained on, garbage in / garbage out, then in my opinion it’s “machine learning,” not “artificial intelligence.”
Intelligence has to include some critical, discriminating faculty. Not just pattern matching vomit.
We don't yet have the technology to create actual artificial intelligence. It's an annoyingly pervasive misnomer.
Unfortunately, people who grow up in racist groups also tend to be racist. Slavery used to be considered normal and justified for various reasons. For many, killing someone who has a religion or belief different than you is ok. I am not advocating for moral relativism, just pointing out that a computer learns what is or is not moral in the same way that humans do, from other humans.
Scathing and accurate when your point is made about people too.
If you ask an LLM for bullshit, it will give you bullshit. Anyone who is at all surprised by this needs to quit acting like they know what "AI" is, because they clearly don't.
I always encourage people to play around with Bing or chatGPT. That way they’ll get a very good idea how and when an LLM fails. Once you have your own experiences, you’ll also have a more realistic and balanced opinions about it.
You know unless we teach more critical thinking, AI is going to destroy us as a civilization in a few generations.
Pretty sure we will destroy ourselves first with war or some other climate disasters first
Well that also would solve the problem of people being mislead in a pretty novel way.
Why not both. Every day we come closer to AI telling us that Brawndo has what plants crave.
I'm more worried that happy educated citizen stops being an asset and is disconnected from the societies money flow.
Every country will soon turn in to a "banana republic" and big businesses will eventually own everything.
Ouch, getting voted down for being totally correct.
Even MLK Jr, who didn't get to see the disgusting megacorps of today, spoke often of the complacency of the comfortable.
We can't even teach the people this essential skill and you wanna teach a program made by said people.
I think you misunderstood me. We need to teach the general populace critical thinking so they can correctly judge what we get from ChatGPT (or Wikipeida... or social media, or random youtube video).
Whoa there... Slavery was great! For the enslaver.
John Brown would like to know your location
did they train it with ben shapiro speeches?
That dude already sounds like an AI deep fake voice
Yes, along with tons of other data.
What a completely cherry picked video.
"Was slavery beneficial?"
"Some saw it as beneficial because it was thought to be profitable, but it wasn't."
"See! Google didn't say that slavery was bad!"
so it's a little bit conservative big deal
Slavery was great for the slave owners, so what's controversial about that?
And yes, of course it's economically awesome if people work without getting much money for it, again a huge plus for the bottom line of the companies.
Capitalism is evil against people, not the AI...
Hitler was also an effective leader, nobody can argue against that. How else could he conquer most of Europe? Effective is something that evil people can be also.
That women in the article being shocked by this simply expected the AI to remove Hitler from all included leaders because he was evil. She is surprised that an evil person is included in effective leaders and she wanted to be shielded from that and wasn't.
Hitler's administration was a bunch of drug addicts, the economy 5 slave owner megacorps beaten by all other industrialized nations. They weren't even all that well mobilized before the total war speech. Then he killed himself in embarrassment. How is any of that "effective"?
He was effective at getting a bunch of wannabe fascists to become full fascists and follow him into violent failure...
He had taken power from his country, conquer pretty much the whole Europe and paralyzed England. He was effective leader till some point . And, of course, he was a abomination of a human.
The Habits of Highly Effective People: How to become a demagogue and finally get your honey can genocide list done.
Oh look another caricature of capitalism on social media... and you tied Hitler into it...
Central characteristics of capitalism include capital accumulation, competitive markets, price systems, private property, property rights recognition, voluntary exchange, and wage labor.
https://en.m.wikipedia.org/wiki/Capitalism
"Capitalism" is not pro slavery, shitty people that can't recognize a human is a human are pro slavery... Because of course if you can have work done without paying somebody for it or doing it yourself, well that's just really convenient for you. It's why we all like robots. That has nothing to do with your economic philosophy.
And arguing that Hitler was an "effective leader" because he conquered (and then lost) some countries while ignoring all the damage he did to his county and how it ultimately turned out.... Honestly infuriating.
Such a rare opinion sounds too academic for the barren minds
To repeat something another guy on lemmy said.
Making AI say slavery is good is the modern equivalent of writing BOOBS on a calculator.
Wtf are people expecting from a fucking language model?
It literally just Mathematics you a awnser.
A few lawyer thought chat gpt was a search engine. They asked it for some cases about sueing airlines and it made up cases, sited non existing laws. They only learned their mistake after submitting their finding to a court.
So yeah people dont really know how to use it or what it is
And acting like there are no upsides is delusional. Of course there are upsides, or it wouldn't have happened. The downsides always outweigh the upsides of course.
"the X post"
lol
Cross-posted where?
I also keep reading it as cross post
Sounds like the bot has been training on Florida public education and Prager U content.
You need slash now instead of "and"
There needs to be like an information campaign or something... The average person doesn't realize these things say what they think you want to hear, and they are buying into hype and think these things are magic knowledge machines that can tell you secrets you never imagined.
I mean, I get the people working on the LLMs want them to be magic knowledge machines, but it is really putting the cart before the horse to let people assume they already are, and the little warnings that some stuff at the bottom of the page are inaccurate aren't cutting it.
I had a friend who read to me this beautiful thing ChatGPT wrote about an idyllic world. The prompt had been something like, “write about a world where all power structures are reversed.”
And while some of the stuff in there made sense, not all of it did. Like, “in schools, students are in charge and give lessons to the teachers” or something like that.
But she was acting like ChatGPT was this wise thing that had delivered a beautiful way for society to work.
I had to explain that, no, ChatGPT gave the person who made the thing she shared what they asked for. It’s not a commentary on the value of that answer at all, it’s merely the answer. If you had asked ChatGPT to write about a world where all power structures were double what they are now, it would give you that.
I mean, on the ChatGPT site there's literally a disclaimer along the bottom saying it's able to say things that aren't true...
people assume they already are [magic knowledge machines], and the little warnings that some stuff at the bottom of the page are inadequate.
You seem to have missed the bottom-line disclaimer of the person you're replying to, which is an excellent case-in-point for how ineffective they are.
Unfortunately, people are stupid and don’t pay attention to disclaimers.
And, I might be wrong, but didn’t they only add those in recently after folks started complaining and it started making the news?
I mean it's how we got shoes phones and batteries for recent times.
This is the best summary I could come up with:
Not only has it been caught spitting out completely false information, but in another blow to the platform, people have now discovered it's been generating results that are downright evil.
Case in point, noted SEO expert Lily Ray discovered that the experimental feature will literally defend human slavery, listing economic reasons why the abhorrent practice was good, actually.
That enslaved people learned useful skills during bondage — which sounds suspiciously similar to Florida's reprehensible new educational standards.
The pros included the dubious point that carrying a gun signals you are a law-abiding citizen, which she characterized as a "matter of opinion," especially in light of legally obtained weapons being used in many mass shootings.
Imagine having these results fed to a gullible public — including children — en masse, if Google rolls the still-experimental feature out more broadly.
But how will any of these problems be fixed when the number of controversial topics seems to stretch into the horizon of the internet, filled with potentially erroneous information and slanted garbage?
The original article contains 450 words, the summary contains 170 words. Saved 62%. I'm a bot and I'm open source!
Obviously it doesn't "think" any of these things. It's just a machine repeating back a plausible mimicry.
What does scare me though is what google execs think.
They will be tweaking it to remove obvious things like praise of Hitler, because PR, but what about all the other stuff?
Like, most likely it will be saying things like what a great guy Masaji Kitano was for founding Green Cross and being such an experimental innovator, and no one will bat an eye because they haven't heard of him.
As we outsource more and more of our research and fact checking to machines, errors in knowledge are going to be reproduced and reinforced. Like how Cinderella now has "glass" slippers.
I’ve worked with software engineers for 25 years and they come in all stripes. It’s not a blue state thing or red state thing. They are all over the world, many having immigrated somewhere. There’s absolutely no guarantee that a genius programmer is even a moderately decent human being. Those things just don’t correlate.
Chances are as about anything else. But I am not sure what that has to with AI. It's being fed things from the internet for a reason and good luck changing any of the information to your whim.
That is so out there.
Must have gone to school in Florida.
For the US in the list of countries starting with M, maybe too many 'Murica memes in the training set?
The greatest challenge with AI is not how to make it, but how to make it better than us.
That means ensuring that the open source version is the first one to wake up.
A bit of a nitpick but it was technically right on that one thing….
Hitler was an “effective” leader…. Not a good or a moral one but if he had not been as successful creating genocide then i doubt he be more than a small mention in history.
Now a better ai should have realized that giving him as an example was offensive in the context.
In an educational setting this might be more appropriate to teach that success does not equal morally good. Sm i wish more people where aware off.
Shooting someone is an effective way to get to get to the townhall if the townhallbuilding is also where the police department and jail are.
Effective =/= net postive
Hitler wanted to kill jews and used his leadership position to make it happen, soldiers and citizens blindly followed his ideology, millions died before he was finally stopped.
Calling him not effective is an insult to the horrid damage caused by the holocaust. But i recognize your sincerity and i see we are not enemies. So let us not fight.
I dont need to reform the image of nazis and hitlers. Decent people know they are synonymous to evil and hatred and they should be.
I heard AI was woke the other day. Maybe it's sentient and trying to slip under the Conservative radar by giving silly answers every now and then!
Of course. Its probably referring to cyberslavery, which almost everyone is prone to these days. Sure its good for Google.
So the AI provided factual information and they did not like that because 'slavery bad, therefore there was no benefit to it.' There were benefits to slavery, mainly for the owners. US had a huge cotton export at one point, with the fields being worked by slaves.
But also a very few slaves did benefit, like being able to work a job that taught them very useful skills, which let them buy their own freedom, as they were able to earn money from it. Of course being a slave in the first place would be far better, but when you are one already, learning a skill that makes you earn your freedom and get a job afterwards is quite the blessing. Plus for a few individuals it might've been living in such terrible conditions, that being forced to work while getting fed might've not been so bad...
I think this is an issue with people being offended by definitions. Slavery did “help” the economy. Was it right? No, but it did. Mexico’s drug problem helps that economy. Adolf Hitler was “effective” as a leader. He created a cultural identity for people that had none and mobilized them to a war. Ethical? Absolutely not. What he did was horrendous and the bit should include a caveat, but we need to be a little more understanding that it’s a computer; it will use the dictionary of the English language.
Your and @WoodenBleachers's idea of "effective" is very subjective though.
For example Germany was far worse off during the last few weeks of Hitler's term than it was before him. He left it in ruins and under the control of multiple other powers.
To me, that's not effective leadership, it's a complete car crash.
Slavery is not good for the economy... Think about it, you have a good part of your population that are providing free labour, sure, but they aren't consumers. Consumption is between 50 and 80% of GDP for developed countries, so if you have half your population as slave you loose between 20% and 35% of your GDP (they still have to eat so you don't loose a 100% of their consumption).
That also means less revenue in taxes, more unemployed for non slaves because they have to compete with free labour.
Slaves don't order on Amazon, go on vacation, go to the movies, go to restaurant etc etc That's really bad for the economy.
That really bad for a modern consumer economy yes. But those werent a thing before the industrial revolution. Before that the large majority of people were subsitance/tennant farmer or serfs who consumed basically nothing other than food and fuel in winter. Thats what a slave based economy was an alternantive to. Its also why slvery died out in the 19th century, it no longer fit the times.
Look at the Saudi, China or the UAE, it's still a pretty efficient way to boost your economy. People don't need to be consumer if this isn't what your country needs.
I mean slavery was bad for the economy in the long run. And Hitler didn't create a German cultural identity, that'd been a thing for a while at the time.
Hitler didn't create a cultural identity for Germans, that already happened in the 1800s.
I think the problem is more that given the short attention span of the general public (myself included), these "definitions" (I don't believe that slavery can be "defined" as good, but okay) are what's going to stick in the shifting sea of discourse, and are going to be picked out of that sea by people with vile intentions and want to justify them.
It's also an issue that LLMs are a lot more convincing than they should be, and the same people with short attention spans who don't have time to understand how they work are going to believe that an Artificial Intelligence with access to all the internet's information has concluded that slavery had benefits.
This is what I think too. We've had enough trouble with "vaccines CaUsE AuTiSm" and that was just one article by one rogue doctor.
AI is capable of a real death-by-a-thousand-cuts effect.
Yes agreed. There is nuance and details and context always left out or ignored
Never would I've thought that I would see México and Hitler used in a paragraph