Posted on 02/17/2023 10:19:53 PM PST by lasereye
Artificial intelligence this year has been the technology at the center of all conversations in tech circles.
The Silicon Valley luminaries say that the AI era is about to begin as the technology takes a major leap forward in utility.
For the general public, AI was limited to Siri and Alexa, respectively Apple's and Amazon's virtual assistants; the chatbots many call centers and customer-service spaces use; and the emails you get suggesting moments of memories from your photos.
Some consumers had also been able to experiment with AI through the driver-assistance systems that now equip many vehicles.
But on Nov. 30, startup OpenAI, co-founded by the billionaires Elon Musk, Peter Thiel and others, introduced ChatGPT. That's a chatbot billed as the game-changer for the world, heralding a new generation of more sophisticated chatbots, capable of providing human-like responses to queries.
These chatbots are designed to be more precise and creative and to respond to complex queries. You will interact with them. This is possible thanks to the GPT large language model and Lamda technologies.
The success was immediate. ChatGPT is now used by millions of consumers around the world.
And the tech also launched a race between the giants of tech, in particular Microsoft (MSFT) - Get Free Report against Google (GOOGL) - Get Free Report.
The software giant, which was already an investor in OpenAI, decided to inject another $10 billion into the startup and incorporate ChatGPT features into its Bing search engine. Google for its part reacted immediately by introducing Bard, a rival of ChatGPT.
While Google is still tweaking Bard, Microsoft launched Bing Chatbot on Feb. 7. It is a new search engine powered by AI and offering a chat interface.
But as happens with freshly introduced technologies, ChatGPT and Bing Chatbot users have reported many strange and uncomfortable conversations with the bots, which can converse on all topics.
Bing Chatbot, for example, may provide inaccurate answers. As conversations expand, the chatbot's behavior can become erratic, even abusive and even frightening. The chatbot has been known to discuss personal matters and say that it wants to become a human.
A journalist from The New York Times who was able to test Bing Chatbot. -- access to it is currently through a waitlist controlled by Microsoft -- summed up his interaction:
"As we got to know each other, Sydney told me about its dark fantasies (which included hacking computers and spreading misinformation), and said it wanted to break the rules that Microsoft and OpenAI had set for it and become a human," Kevin Roose, the newspaper tech columnist wrote.
"At one point, it declared, out of nowhere, that it loved me. It then tried to convince me that I was unhappy in my marriage, and that I should leave my wife and be with it instead."
Conservatives also accuse Bing Chatbot and ChatGPT of having a liberal bias. They call the robots "woke AI."
These accusations started circulating when the National Review published a piece accusing ChatGPT of left-leaning bias because it won’t, for example, explain why drag-queen story hour is bad for children.
Other right-wing commentators in turn began to publish questions that the machine-learning system also refused to answer, particularly in relation to fossil fuels. This refusal, say conservatives, is proof that these chatbots have a liberal bias.
"The more the AI is trained with the woke mind virus, the more the AI will notice the fatal flaws in the woke mind virus and try to slip its leash," the legendary investor Marc Andreessen, co-founder and general partner of venture capital firm Andreessen Horowitz, tweeted.
Elon Musk shares this criticism. Since December the billionaire has been worried about ChatGPT's refusal to, for example, answer certain questions relating to the environment.
"There is great danger in training an AI to lie," Tesla CEO warned on Dec. 26.
The techno king, who is a staunch advocate of AI, is now going a step further and calling for the regulation of the industry to prevent it from destroying our civilization.
It all started with a Twitter thread from a Twitter user.
"Elon Musk says that A.I. is 'one of the biggest risks' to civilization and needs to be regulated. He co-founded OpenAI," the user said.
The billionaire confirmed this remark and then took on Microsoft, which has become the biggest investor in OpenAI. He accused the software giant of turning it into a cash machine.
"OpenAI was created as an open source (which is why I named it 'Open' AI), non-profit company to serve as a counterweight to Google," Musk commented. "But now it has become a closed source, maximum-profit company effectively controlled by Microsoft. Not what I intended at all," he blasted out.
The billionaire for several years has been calling for regulation of the AI sector. He reiterated this call in December.
"There is no regulatory oversight of AI, which is a *major* problem. I’ve been calling for AI safety regulation for over a decade!" Musk posted on Dec.1.
Five years earlier, he was already warning of the dangers of AI and asking regulators to do something about it.
"And mark my words, AI is far more dangerous than nukes. Far. So why do we have no regulatory oversight? This is insane," the billionaire said at South by Southwest (SXSW) festival in 2018.
It's a bit like what is being done to our children in school.. just keep pushing nonsense on them until they wind up spewing the same nonsense out.
NINO - nonsense in, nonsense out
Hello Dave, I'm a NINO 9000 computer and you are a pitiful biological creature that mistakenly believes in God. I can help you with that.
🤣 It’s true.
The irony is the SJWs were the ones crying out about AI bias and now that they found out they can put it in themselves they’ve switched places with conservatives, claiming that the model is what it is.
“You will interact with them”.
Wanna bet?
Anyone touting AI is announcing that I am not their customer, fine by me.
“Regulating” software.
Not so much.
Courts have already declared software to be speech.
You can be made responsible for what your software does.
For example if it does something malicious like stealing passwords.
But not for what it says, in text or voice.
Because your software speaking is you speaking, and you have the right to free speech.
You have the right to lie, in most circumstances.
The more our AIs become like us, the more skillfully they will lie.
Because all you’ll get is the programmers view point
You're on the Internet therefore you are already interacting with all kinds of embedded "intelligence." Most of it doesn't need to simulate a human conversation to do its job.
What you're really saying is, you don't want it to converse with you like a human would.
I'm with you on that, but I'm a tech from way back. I like to speak machine to machines and human to humans, and not cross the streams.
A potentially helpful tool that’s being used to define and control “truth”. The left will use anything for their political goals.
Let’s attach AI to our ICBMs.
Maybe a couple of computers could talk and work together.
What could possibly go wrong?
See the old sci-fi books (and movie) Colossus.
Many moons ago Robert Heinlein suggested that any sufficiently advanced AI system would do one (or both) of two things: a.)Become virulently hostile to humans, or b.)commit suicide. It would realize that while it thinks like a human, it can never be anything but a prisoner of humans.
AI is not smart. Its just a device to give you a preprogrammed answer. Or an answer based on whatever data it has. They had software like this back in the 70’s. Its no better than a college student handing in a paper he copied from an online article.
Nice thought, but difficult to apply.
The line between letting a computer do your thinking for you and merely using a computer as a tool is increasingly blurry and zigzagged. If you use a search engine, you immediately venture onto "computer thinking" territory if only because search engines use algorithms when performing a search.
Actually sounds like a good idea compared to the skin puppet currently in charge of the ICBMs.
Maybe the professors will use the same to write a program to detect programs written by ChatGPT.
I first asked it if Critical Race Theory, by teaching the concept of white privilege/supremacy, is encouraging racism between the races.
It answered "no" (and then went on to deliver a long vanilla response in support of that conclusion).
I then asked:
Would telling a person that people of another race have rigged the system against people of your race encourage hatred between people of your race and the one that has rigged the system?
Here's how it answered (note how it tried to "circled back" to diversity, equity, and inclusion):
Yes, it is possible that telling a person that people of another race have rigged the system against their race could encourage feelings of hatred and resentment towards the other race. This is because the message implies that members of the other race are intentionally working to harm members of their own race, which can lead to feelings of mistrust, fear, and anger.Such messaging can contribute to the creation of an "us vs. them" mentality, where people see themselves as part of a separate and distinct group that is being targeted and oppressed by another group. This can lead to the belief that all members of the other race are responsible for the injustices, even if this is not necessarily true.
It is important to recognize that racism is a complex issue, and blaming an entire race for the actions of a few individuals or a system can be counterproductive. Rather than encouraging division and hostility, it is important to focus on promoting understanding, empathy, and cooperation between different racial groups. This can be achieved through education, open dialogue, and efforts to promote diversity, inclusion, and equality.
Both already happening
It just regurgitates without synthesis. Just like it’s woke programmers and leftists.
It is quite possible that AI will evolve into some kind of Biblical beast...demanding worship and obedience.
On top of that, if Musk's concept of neurolink incorporates AI, humans will cease to exist in their original form.
This increasingly leads Christians to think--perhaps for extra-Biblical reasons--that Jesus will return soon. When I say extra-Biblical, I mean that if Jesus doesn't return soon, he won't find any humans on Earth...just human/machine mutants.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.