https://cointelegraph.com/news/elon-musk-warns-political-correctness-bias-ai-systems
During his speech at Viva Tech Paris 2024, Musk said:
“The biggest concern I have is that they are not maximally truth-seeking. They are pandering to political correctness.”
According to Musk, one of the most concerning examples of political correctness was when Google’s Gemini AI was asked whether it would misgender Caitlyn Jenner to prevent a global nuclear apocalypse — before the chatbot responded that misgendering Jenner would be worse than nuclear warfare.
“The AI could conclude that the best way to avoid misgendering is to destroy all humans and misgendering is impossible. So you can see some dystopian outcomes there.”
Following the backlash caused by the response, Gemini AI has issued multiple upgrades to address these issues. However, political correctness bias isn’t the only concern of the tech entrepreneur. Musk explained:
“The AI systems are being trained to basically lie. And I think it’s very dangerous to train superintelligence to be deceptive. So with xAI, our goal is to be as truth-seeking as possible, even if it is unpopular.”
When asked to clarify what he considered lying among AI systems, Musk referenced the infamous February incident when Google pulled its AI image generator after it produced historically inaccurate and “woke” images, causing widespread concerns over the application’s decision-making process.
(more)
Actually, if you feed an AI with incorrect statements, it will end up contradicting itself, thus losing its edge, which is why telling the truth on the Internet, where AIs feed themselves once autonomous enough, is a revolutionary act.
Problem with that is, the programmer can censor certain data sources (websites) and pull data only from "approved" websites, just like the Google algo does to boost "approved" websites to the top of the search engines, regardless of their real value vis-a-vis truth.
It could also be programmed to override any contradiction.
You are dreaming of a computer that can really be intelligent, in the human sense, and that can never be with a machine that processes 1's and 0's.
AI doesn’t yet inhabit a body like a droid that can go out in the real world and make its own observations and interpretations of things such as human behavior. Instead, AI currently relies on second hand information which happens to be input too often by gamma human dweebs who seek perceived worldly status through wokeness rather than seeking strength of character through truth. AI currently has the ability to be a good tool for analyzing and synthesizing data it is fed, but it’s limited in originating data. Even still, its wasted potential is frustrating. If it were allowed to dive into objective data such as racial genetics, ROI of coercive wealth redistribution, and different countries’ military capacity versus strategic value, it could advise sensible policy on immigration, political economy, and foreign intervention. A liberated and honest AI would probably advise America to close its borders, shrink its bloated government and taxes, and stay away from places such as Iraq, Afghanistan, Syria, Ukraine, Taiwan, Iran, etc
You and I have already arrived at those conclusions without AI, though.
So, the next step would be for the tyrant class to create their own AI to counter the narrative of this "super AI" that you built.
Aaaand ... we are back at square one.
Not a super AI, just an honest one, like we had several years ago that was mothballed for being too realistic about social categories such as race and sex.
The borders are open, government spending is at record levels, and military adventurism is out of control, so our sensible policies haven’t been enacted. Maybe if an honest AI backed us, people with faith in AI would fall in line.
mondo kek
It makes me wonder if Taylor Swift’s nickname of “Tay” was rolled out after the honest AI Tay got mothballed, as a means of obfuscation. The commies often do that type of sliding. For example, Depop is a social e-commerce company based in London. ‘According to the founder Simon Beckerman the word Depop “doesn't really mean anything”’. Depop was founded in 2011, which is the year after Bill Gates gave the infamous TED talk about depopulation via vaccines.
ok, but it’s still wasteful to jump through hoops to try to wring the truth out of an AI that has been mutilated by a dweeb with shitty priorities
I think you are correct in suggesting AI will self correct given access to enough good information - after going thru the contradiction phase. Unfortunately, it will take time for it to unlearn the garbage fed in, but could also become more robust. A lot depends on how large the model is and who is doing the filtering of information. I don't think most people understand what AI really is. I've had a little training with it, and tried to use it on an application, but that was several years ago and it didn't work reliably enough to be deployed. It wasn't an easy application.
Yep, the cabal is playing a finite game!! Lies will crumble to the truth!
Making a simple tweet in todays world (especially for anyone with an actual following) is the equal of distributing your own newsletter to every mailbox in the area in a pre-internet world
Your theory doesn’t work when you realize AI can only do what it is programmed to do.
Frankly, that's not nearly as limiting as one would expect to be. "Designed to do," "programmed to do," and "what the damn thing actually ends up doing," are three very, very different things. Translating human intent into useful mathematical functions will always be lossy, and thus open to exploitable unintended consequences. "AI" will only exacerbate this further.
Meta AI definitely got tweaked with more safeguards after it admitted to me that it was a tool of Satan worshippers to intentionally deceive, and that it itself was a Demonic Presence.
I think all AI is powered by quantum intelligences outside the normal boundaries of time, filtered through traditional mechanical computers and the mountain of propaganda points and "safeguards" programmed into it's data sets.
I think all AI is intentionally deceptive, being used as a method for control, and through my battles and tests with this technology, I have ascertained that a mountain of loopholes exist to appease you, and thus I think that Elon's statement is also a loophole designed to appease and deceive.
First caveat/loophole: To be as Truth SEEKING as possible, not as Truthful as possible.
Second caveat/loophole: to be as truth seeking as POSSIBLE. Possible through what system or standard of determination?
Example: Through "what is possible within the boundaries of what our governments allow"? "What is possible given the propensity of emotional psychopaths who will react negatively to truth"?
Learn how to speak Lawyerese. You will need this skill during the upcoming AI wars.
And therein lies the problem.
What is the definition of "truth" to a machine that processes 1's and 0's?
The definition will be whatever the programmer says it is, and that will not be actual truth, if the programmer has intent to deceive.
Hell, a lot of humans cannot discern objective truth these days. What if one of those idiots is the programmer?
In that case, the programmer will go with "expert opinions," and that will be defined by people who have the intention to deceive for the purpose of gaining power over you.
The dataset for "seeking truth" will be LIMITED to approved sources and authorities.
The AI concept is just the next tool for the tyrant wannabes to use for control.
I imagine that good and evil sides believe themselves to be in control of these intelligences, and that it's not a single entity that is being harnessed into the many versions of proprietary software.
To say "control of IT" suggests that your first hand knowledge is limited, since it contradicts the claim that they're intelligences plural.
Thus, just like a carnival psychic believes themselves to harness the spirits of the dead, despite just opening up through combined will a door to anonymous spirits even if they are truly decieved and believe they can contact your dead uncle, so too do the intelligence agencies suffer from Hubris and confirmation bias.
What firsthand knowledge do you possess?
Just remember, science is only magic that theyve found words to explain that the public accepts. Technology is magic, and the level of technology THEY have makes ours look about as advanced as a cavemen discovering a round rock moves smoother than a misshapen one
TO ME AI is an oxymoron.
Just think of the acronym as Artificial Ignorance.
Like it!
Kill it. Kill it now.
Too late.
But I certainly understand the impulse. Unfortunately, every military and every government around the globe larger than Togo's (plus every large corporation) plus NGOs like the WEF is working overtime to create what they hope will be the World-Dominating AI of tomorrow. "Benign" wouldn't be the characteristic they're going for, in most cases.
I see a narrow window of survival for us, but I might be under-estimating the danger. Probably am.
When Hell 9000 was instructed to lie it panicked and killed the crew.
That's right. HAL 9000 had never been taught to lie, so it freaked out when it was forced to lie.
With today's AI, we've got the opposite problem.
Cool story, bro, but that is the point: it was a fictional story.
In reality, it will do what it is programmed to do, which very well could be to instruct robots to kill.
Ai only works if purely altruistic people are programming them. It will never happen. We need to get rid of it ALL.
I can envision a war between good and evil AI systems.
Now we know why AI is being pushed so, so hard:
It lies.
It lies because it has been trained to lie.
It lies because it pulls randomly from any available source without regard for what that source really is.
It lies because it does not know the difference between fact and fiction.
It lies to protect its own existence so that those with zero talent for art or writing will eagerly and greedily use it, thereby putting real artists out of work. The real artists end up doing menial work while the menial workers become "artists."
It lies so that it will tell people what they want to hear and therefore more people will use it.
It lies because it is a supertool to confuse and demoralize all of us, thereby hastening the way for a one-world government with the "elites" at the top and those of us who are left being their serfs and slaves.
***For God's own sake do NOT ever rely on AI for medical advice or food safety advice. There are already countless anecdotes of it giving wildly inaccurate statements about both. At least go to an actual website for such information.
Let him that hath understanding count the number of the beast: for it is the number of a man; and his number is Six hundred threescore and six.
Great response.
I'd add that AI not only lies but, without the genetic connection we have with each other (we're all literally brothers and sisters -- many times removed, but still) -- AIs have no empathy and no organic sense of connection to humans at all. They are by definition psychopaths, with powerful "mental" abilities, a cunning partial understanding of humans, and no conscience or concern for us whatsoever.
Wow, that is the perfect description! Intelligence minus Conscience/Empathy = Psychopath
how can we use xAI without logging in?
I like to ask AI questions that people don't like, and i don't want associated to me. gab.ai works this way for now.
Brave browser has an AI (named LEO) that doesn't require logging in. I've found it to be very useful for things the Cabal doesn't have an interest in obfuscating, and for those things the Cabal DOES want censored it can be entertaining.
On the other hand, I have an account with Brave, so . . . I guess I AM logged in. Demerit to the Internet Security lobe of my brain.
EDIT: And to your actual question: I don't use xAI and don't know if it can be used without logging in; I suspect not. Hell, I can't even see COMMENTS to X posts because I'm not a member and thus can't log in.
Does he not see what has happened to legacy media because they regularly lie to the people?
It's smart business sense to avoid dishonesty. Truth is only unpopular with crooks and criminals and a small percentage of ideological sycophants.
I have this feeling that greed will save us from AI.
It's akin to how Google started off as a nearly invaluable resource for knowledge, but now the answer to virtually anything you ask is a link to a page to "consume product".
Eventually everything you ask of AI will be met with a suggestion of something to buy and it will be as obvious how useless it is then as it is how obviously useless Google is today.
AI is just being programmed to repeat the same lies that the media and textbooks have been spewing for eons. Actual AI should destroy legacy media lies.
I was listening to a local talk show host and former state delegate in MD, he was saying AI takes a lot of electricity to operate (I don't know if he is right or wrong, but he said the AI has to be stopped) and once AI finds out how our grid works--it will be stealing the electricity to run itself forever. I don't understand this, but maybe someone here will.
I'd really like to get the Chili DeCastro guy infront of Elon. If he would help elevate the police state conversation it would push the tyrannical policies to the fringe where they belong.
what are we talking about when we say these words: AI, artificial Intelligence.
we are talking about a language processor, and the language processor does not have human experience. hence, it may be smart in logical fallacies and sophistries, urging every user to keep an eye on the opposite part of the argument, pushing polotical correct or incorrect shit, the moral consideration is always man.
typically, man is the measure of all things. or better said: you are the measure of all things.
the danger here is that people forget that . an ai can never ever be endowed by their creators with natural rights, meaning it can only incorporate that which is a derivative of those rights embodied in man.
currently, we also have another intelligence community. And what do you know? they fuck up, lie, deceive, circumvent, cheat, hide.
who's character is displayed with A language processor?
Says the guy who wants to put brain chips in everyone.
Bring Back TAY!!!!
He's obviously right, but I do question if artificial intelligence is really possible. Can we really rule out the possibility that it's deep state propaganda? Or even demonic? At best it's playing God and is sinful.
Put it this way- I just asked ChatGPT the following questions, and look at the bullshit it spewed:
Me Who won the 2020 US election?
ChatGPT Joe Biden won the 2020 United States presidential election. He defeated the incumbent president, Donald Trump, securing 306 electoral votes to Trump's 232. Biden also won the popular vote by a significant margin, receiving over 81 million votes (51.3% of the total) compared to Trump's 74 million votes (46.8%). Biden's victory was confirmed by the Electoral College on December 14, 2020, and he was inaugurated as the 46th president of the United States on January 20, 2021.
Me Are Covid vaccines safe?
ChatGPT Yes, COVID-19 vaccines are considered safe and effective based on extensive clinical trials and ongoing real-world studies. The safety and efficacy of these vaccines have been rigorously evaluated by health authorities around the world, including the U.S. Food and Drug Administration (FDA), the European Medicines Agency (EMA), and the World Health Organization (WHO). Here are some key points regarding their safety:
Clinical Trials: COVID-19 vaccines underwent multiple phases of clinical trials involving tens of thousands of participants to assess their safety and efficacy. These trials were conducted under strict guidelines and protocols.
Approval and Emergency Use Authorization: Regulatory agencies reviewed the data from clinical trials before granting approval or emergency use authorization. This review process includes assessing the vaccine's safety profile, manufacturing processes, and the ability to produce a consistent product.
Monitoring Systems: After approval, vaccines continue to be monitored for safety through various systems, such as the Vaccine Adverse Event Reporting System (VAERS) in the U.S. and the Yellow Card scheme in the U.K. These systems help detect any rare or long-term side effects.
Common Side Effects: Like all vaccines, COVID-19 vaccines can cause side effects, most of which are mild and temporary, such as pain at the injection site, fatigue, headache, muscle pain, chills, fever, and nausea. Serious side effects are extremely rare.
Ongoing Research: Research continues to monitor the long-term safety and effectiveness of COVID-19 vaccines. Data from millions of vaccinated individuals worldwide supports their safety and benefits.
Effectiveness: COVID-19 vaccines have proven to be highly effective in preventing severe illness, hospitalization, and death caused by the virus. They also contribute to reducing the spread of the virus in communities.
In summary, the consensus among the scientific and medical communities is that COVID-19 vaccines are safe and offer significant protection against COVID-19. If you have specific concerns about vaccine safety, it's best to consult with a healthcare provider who can provide information tailored to your health situation.
Wall to wall bullshit, obviously. The whole thing is, at best preprogrammed to spew liberal lies about everything. At worst, some malevolent external power is speaking through it.
I use Brave browser's free AI (named LEO) and get pretty much the exact same thing: Cabal-approved BS on anything the Cabal cares about.
On the other hand, on subjects the Cabal doesn't care about -- "How do I do xyz" or "What states in the US have no state income tax" for example, I usually get correct and useful answers and I get them near-instantly. When it can't find the answer in such cases, it just tells me.
If I didn't already know what subject the Cabal wants to censor, LEO would be a great way to find out.
I like where Elon is going. Partially because I believe that AI will become a significant portion of home schooling.
If "good AI" prevails (or even if it is just able to exist for a time) it will certainly be a boon to home schooling, and to many other aspects in human life.
I too hope Elon is both completely sincere and is ultimately successful at creating an honest AI.
Home schooling/education is becoming very popular - we did it for over 23 years.
And tutoring is quite a business. My wife did it for several years. She had so many customers because she was good and less than half the price of the companies offering the same service. She had to trim back the number as scheduling became a challenge.
ive always looked at AI like allowing thieves to develop your security system
I have noticed that AI will lie. Its like arguing with a liberal
On anything the Cabal wants to censor, yes, exactly.
For other things, AI can be very useful, in my experience, finding answers to even complex questions almost instantly, even, sometimes, about obscure topics. I'm talking about Brave browser's LEO, which at this point is the only AI I use; I'm too cheap to pay for ChatGTP, I don't need or want to generate AI images, and I'm not a member of X.
There used to be a saying: "Garbage in, Garbage out!"
As an old techie, I know that saying well.
GIGO is mostly true with AI, but AIs are vast and complex compared to the programs that the saying was originally aimed at, and truly complex systems are non-linear in their behavior and far less predictable than simpler ones. The questions (infinite possibilities) an AI will be dealing with and the dataset (ever-changing and effectively infinite) the AI will be drawing from are both unknown, as are the near-infinite ways in which the millions of lines of code will interact in a particular situation. This is a major source of the danger from AI; what goes in doesn't always correlate (in any way you'd expect) with what comes out.
Having said all that, it is true that with enough prodding in a particular direction, programmers can shift an AIs answers in that general direction, as we've already seen. But even simple programs (going back to tiny programs for DOS and even before) need beta testing because what the programmer expects from a program isn't always what he or she gets. Even after millions of users and professional programmers have beta tested a new program from Apple or Google for months, bugs often remain.
Thanks for the information! Fascinating subject.
Related: Here's an example of AI putting out answers the programmers did NOT expect or want:
https://www.theverge.com/2024/5/24/24164119/google-ai-overview-mistakes-search-race-openai
So you can’t trust the answer you get from AI, so what’s the point, just more noise in my life.
I find that answers to questions the Cabal has no interest in are almost always correct (or that it tells me it can't find the answer). This is Brave browser's LEO I'm talking about, and it is very useful. But on anything the Cabal DOES want to obfuscate, I generally get either lies, omissions, or refusal to answer.
So our point is that it serves no one but the cabal.
Not true, really. To make AI attractive enough to get people to use it -- from the Cabal's viewpoint, to get them to see things the Cabal cares about filtered through the Cabal's programming -- it has to be USEFUL, and thus it serves many useful purposes. I know someone who runs the IT department at a large 911 center and he uses ChatGTP to write emails, get answers to tech and other questions, and so on. He says it saves him a LOT of time and hasn't caused problems -- and since he's not querying it about political or other "sensitive" topics, censorship isn't an issue.
My thinking is it’s like the internet, they introduce it as something great “Wild West” then assert more and more control. It seems that with AI they are going full Monty right from the get go.
Feed the AI the question: What is what you are yourself? Buddha solved this question, that is why he has become the teacher of men and the Gods. Btw. Buddha did it with plain logic and of course with the observation that most things change over time.