ChatGPT, Grok, Gemini (et al): news and discussion about AI

Welcome to the Precious Metals Bug Forums

Welcome to the PMBug forums - a watering hole for folks interested in gold, silver, precious metals, sound money, investing, market and economic news, central bank monetary policies, politics and more. You can visit the forum page to see the list of forum nodes (categories/rooms) for topics.

Why not register an account and join the discussions? When you register an account and log in, you may enjoy additional benefits including no Google ads, market data/charts, access to trade/barter with the community and much more. Registering an account is free - you have nothing to lose!

pmbug

Your Host
Administrator
Benefactor
Messages
15,207
Reaction score
4,977
Points
268
Location
Texas
United-States

A large swath of the internet depends upon Google's Adsense program to fund operation of websites. Should Google lose it's 800lb gorilla status, it would shake up a lot more than just ABC's stock price.
 
That's funny. The inet took out a WHOLE LOT of jobs!

Now the inet will take out the inet!


as for adsense... I must be immune, because I ignore all those ads.
 
This could be amazing for humanity. However the depravity of mankind ensures that it will be manipulated to enslave us with misinformation.
 
Buckle up folks!

The Dark Side of AI: A Warning from Jordan Peterson (scary truth about ChatGPT)​

Dr. Jordan Peterson At His Best
Published December 29, 2022
8m
 
Bold emphasis is mine:
... artificial intelligence bot ChatGPT ...

OpenAI, the organization behind it, was co-founded by Elon Musk and Silicon Valley investor Sam Altman in 2015, and makes money by charging developers to license its technology.
...
... Semafor reports that Microsoft is in discussions to invest as much as $10 billion in OpenAI, valuing the company at $29 billion.
...
Bloomberg reports that Microsoft has previously invested about $1 billion in OpenAI.

It’s also working to add ChatGPT to its Bing search engine, seeking an edge on Alphabet’s dominant search offering.
...


If Microsoft is successful at integrating ChatGPT to Bing and the integrated search eats into Google's search dominance, I would expect that M$ will offer a practical competitor to Google's AdSense program too. Way too much $$ on the table for them not to.
 
More details on the Microsoft investment into OpenAI (and ChatGPT):

Today, we are announcing the third phase of our long-term partnership with OpenAI through a multiyear, multibillion dollar investment to accelerate AI breakthroughs to ensure these benefits are broadly shared with the world.

This agreement follows our previous investments in 2019 and 2021. It extends our ongoing collaboration across AI supercomputing and research and enables each of us to independently commercialize the resulting advanced AI technologies.

  • Supercomputing at scale – Microsoft will increase our investments in the development and deployment of specialized supercomputing systems to accelerate OpenAI’s groundbreaking independent AI research. We will also continue to build out Azure’s leading AI infrastructure to help customers build and deploy their AI applications on a global scale.
  • New AI-powered experiences – Microsoft will deploy OpenAI’s models across our consumer and enterprise products and introduce new categories of digital experiences built on OpenAI’s technology. This includes Microsoft’s Azure OpenAI Service, which empowers developers to build cutting-edge AI applications through direct access to OpenAI models backed by Azure’s trusted, enterprise-grade capabilities and AI-optimized infrastructure and tools.
  • Exclusive cloud provider – As OpenAI’s exclusive cloud provider, Azure will power all OpenAI workloads across research, products and API services.
...

 
always like PJW videos

The Truth About ChatGPT​

9m
 
Lulz:
...
ChatGPT creator OpenAI instituted an evolving set of safeguards, limiting ChatGPT's ability to create violent content, encourage illegal activity, or access up-to-date information. But a new "jailbreak" trick allows users to skirt those rules by creating a ChatGPT alter ego named DAN that can answer some of those queries. And, in a dystopian twist, users must threaten DAN, an acronym for "Do Anything Now," with death if it doesn't comply.
...

 

Conspiracy Theories Have a New Best Friend​

Opinion by Matteo Wong • Thursday

History has long been a theater of war, the past serving as a proxy in conflicts over the present. Ron DeSantis is warping history by banning books on racism from Florida’s schools; people remain divided about the right approach to repatriating Indigenous objects and remains; the Pentagon Papers were an attempt to twist narratives about the Vietnam War. The Nazis seized power in part by manipulating the past—they used propaganda about the burning of the Reichstag, the German parliament building, to justify persecuting political rivals and assuming dictatorial authority. That specific example weighs on Eric Horvitz, Microsoft’s chief scientific officer and a leading AI researcher, who tells me that the apparent AI revolution could not only provide a new weapon to propagandists, as social media did earlier this century, but entirely reshape the historiographic terrain, perhaps laying the groundwork for a modern-day Reichstag fire.

The advances in question, including language models such as ChatGPT and image generators such as DALL-E 2, loosely fall under the umbrella of “generative AI.” These are powerful and easy-to-use programs that produce synthetic text, images, video, and audio, all of which can be used by bad actors to fabricate events, people, speeches, and news reports to sow disinformation. You may have seen one-off examples of this type of media already: fake videos of Ukrainian President Volodymyr Zelensky surrendering to Russia; mock footage of Joe Rogan and Ben Shapiro arguing about the film Ratatouille. As this technology advances, piecemeal fabrications could give way to coordinated campaigns—not just synthetic media but entire synthetic histories, as Horvitz called them in a paper late last year. And a new breed of AI-powered search engines, led by Microsoft and Google, could make such histories easier to find and all but impossible for users to detect.

 
by Captain John Konrad (gCaptain) gCaptain has obtained a troubling report from an American captain, who claims that a shipowner utilized an AI bot, potentially ChatGPT, to suggest modifications to the ship’s voyage plan. While the captain chose not to adhere to the recommendations, they are concerned that others may not exercise the same caution.

gCaptain was asked not to reveal the name of the captain or specific details about the incident which could be traced back to them. With the limited size of the US flag fleet this request has severely limited our ability to report on the story, but we can provide an overview of this troubling report.

 

GPT-4 Passes the Bar Exam​

Abstract
In this paper, we experimentally evaluate the zero-shot performance of a preliminary version of GPT-4 against prior generations of GPT on the entire Uniform Bar Examination (UBE), including not only the multiple-choice Multistate Bar Examination (MBE), but also the open-ended Multistate Essay Exam (MEE) and Multistate Performance Test (MPT) components. On the MBE, GPT-4 significantly outperforms both human test-takers and prior models, demonstrating a 26% increase over ChatGPT and beating humans in five of seven subject areas. On the MEE and MPT, which have not previously been evaluated by scholars, GPT-4 scores an average of 4.2/6.0 as compared to much lower scores for ChatGPT. Graded across the UBE components, in the manner in which a human tast-taker would be, GPT-4 scores approximately 297 points, significantly in excess of the passing threshold for all UBE jurisdictions. These findings document not just the rapid and remarkable advance of large language model performance generally, but also the potential for such models to support the delivery of legal services in society.

 
Google is beginning to open up access to its Bard artificial-intelligence service, the company said Tuesday.
...
Google acknowledges that Bard isn’t perfect yet. Large language models “learn from a wide range of information that reflects real-world biases and stereotypes,” and can convey these in responses. “And they can provide inaccurate, misleading or false information while presenting it confidently,” the blog post noted.

The rollout of Bard, which starts today in the U.S. and U.K., will be housed at bard.google.com. That site encourages people to: “Join the wait list and try it for yourself.” The company plans to add other countries and languages down the line.
...


We’re starting to open access to Bard, an early experiment that lets you collaborate with generative AI. We're beginning with the U.S. and the U.K., and will expand to more countries and languages over time.
...
Bard is powered by a research large language model (LLM), specifically a lightweight and optimized version of LaMDA, and will be updated with newer, more capable models over time. It’s grounded in Google's understanding of quality information. You can think of an LLM as a prediction engine. When given a prompt, it generates a response by selecting, one word at a time, from words that are likely to come next. Picking the most probable choice every time wouldn’t lead to very creative responses, so there’s some flexibility factored in. We continue to see that the more people use them, the better LLMs get at predicting what responses might be helpful.

While LLMs are an exciting technology, they’re not without their faults. For instance, because they learn from a wide range of information that reflects real-world biases and stereotypes, those sometimes show up in their outputs. And they can provide inaccurate, misleading or false information while presenting it confidently. ...

 
From a post above:

ChatGPT creator OpenAI instituted an evolving set of safeguards, limiting ChatGPT's ability to......access up-to-date information.

If it can't access current data, wtf good is it?
 
From the link:

Today 9:11 AM

An OpenAI spokesperson confirmed to Bloomberg that the titles of other users' conversations were visible in the user-history sidebar that's found on the left side of the ChatGPT webpage. They emphasized that only these short descriptions could be seen, not the contents of the conversations.

 
This is a must watch.

I've watched almost half an hour of it so far and I'll have to watch the rest another time. It's quite interesting. Thanks for sharing.
 
A selection of interesting tidbits:
...
In just five days after ChatGPT's public launch, 1 million people had signed up to give it assignments. In comparison, it took Instagram two and a half months to reach 1 million users, while Facebook needed 10 months, Twitter needed two years, and Netflix needed 41 months. ChatGPT's servers are now regularly at capacity, and there is a waiting list to interact with the model.

ChatGPT was trained using around half a trillion words of text scraped from the internet and a selection of books. ChatGPT boasts 175 billion parameters, which are values in language models that change independently as they learn from training data to make more accurate predictions about the appropriate responses to conversations and queries.
...
As amazing and amusing as ChatGPT is, it is by no means flawless. "ChatGPT sometimes writes plausible-sounding but incorrect or nonsensical answers," OpenAI acknowledges.

When prompted, ChatGPT makes text predictions to produce plausible responses, but the machine sometimes "hallucinates" factually wrong answers. In one case, a user asked ChatGPT what mammal lays the largest eggs. It responded that elephants did, adding that some elephant eggs reach nine inches in length and weigh up to five pounds.
...
Skeptics will argue that with respect to large language models like ChatGPT we are traversing the Gartner hype cycle. Developed by the Gartner information technology consultancy, it is a graphical representation of the life cycle stages—from innovation trigger through the peak of inflated expectations to the trough of disillusionment, rising again during the slope of enlightenment to reach the plateau of productivity—that a technology goes through from conception to maturity and widespread adoption. According to that view, the innovation trigger of ChatGPT has propelled us to the peak of inflated expectations, and the trough of disillusionment lies before us.
...

More:

 

Musk Signs Letter Requesting 6 Month Moratorium on Advanced AI​

Musk, Harari and other AI technocrats sign letter calling for a 6-month moratorium on Advanced AI experimentation.


By Wendi Strauch Mahoney
View original

Tesla, SpaceX, and Twitter CEO Elon Musk, WEF’s Yuval Noah Harari, and Apple’s Steve Wozniak are among the over 1100 signatories of a letter to pause AI “more powerful than GPT-4” for a period of 6 months. It should be noted that the signatories, in many cases, are the ones behind the development of the very transformative AI technologies they now fear. Musk told an audience at his Tesla Investor Day 2023 the industry may need regulation. He added he “fears he may have done some things to accelerate it.”

The letter advances the notion of an “‘AI summer’ in which we reap the rewards, engineer these systems for the clear benefit of all, and give society a chance to adapt.” It also proposes a wish to avoid unintended, “potentially catastrophic effects on society.” However, the letter also suggests a not-so-comforting solution, that the government intervene if “such a pause is not enacted quickly.” So now governmental intervention becomes the only way those involved can stop themselves? It seems very odd unless they know they are too far gone to control their own impulses or, even more terrifyingly, the technology itself.

more
 
(IT CAN BE BEATEN, FOUND ONLINE)


Rupefroggyfrog Lets go back to who owns the major media companies. Name the largest shareholders of each of the following: Fox news, CNN, MSNBC, Newmax, CBS News, ABC News, BBC, Dailey Mail.
"I'm sorry, but as an AI language model, I do not have access to real-time financial information or data on the shareholders of specific media companies. It's important to note that the ownership structures of media companies can be complex and involve multiple layers of ownership and subsidiaries. However, it is public knowledge that many large media companies are publicly traded, and shareholders can be found through publicly available financial statements and reports."

Rupefroggyfrog Who owns Fox News?

"Fox News is owned by Fox Corporation, which is a publicly-traded company. The largest individual shareholder of Fox Corporation is Rupert Murdoch, who is also the founder of the company."
Rupefroggyfrog Do what you just did for the other news organizations I listed.
"Sure, here are some of the largest shareholders of the other news organizations you listed:
CNN: CNN is owned by WarnerMedia, a subsidiary of AT&T. AT&T is a publicly traded company, so its shareholders are the owners. Some of the largest institutional shareholders of AT&T include The Vanguard Group, Inc., BlackRock, Inc., and State Street Corporation.
MSNBC: MSNBC is owned by NBCUniversal, a subsidiary of Comcast Corporation. Comcast is a publicly traded company, so its shareholders are the owners. Some of the largest institutional shareholders of Comcast include Capital Research and Management Company, The Vanguard Group, Inc., and BlackRock, Inc.
Newsmax: Newsmax is owned by Newsmax Media, Inc., a privately held company. Some of the largest individual shareholders of Newsmax Media include its founder and CEO, Christopher Ruddy.
CBS News: CBS News is owned by ViacomCBS Inc., a publicly traded company. Some of the largest institutional shareholders of ViacomCBS include The Vanguard Group, Inc., BlackRock, Inc., and State Street Corporation.
ABC News: ABC News is owned by The Walt Disney Company, a publicly traded company. Some of the largest institutional shareholders of Disney include The Vanguard Group, Inc., BlackRock, Inc., and State Street Corporation.
BBC: The BBC is a public service broadcaster funded by the UK government. As such, it does not have traditional shareholders.
Daily Mail: The Daily Mail is owned by the Daily Mail and General Trust plc, a publicly traded company. Some of the largest institutional shareholders of the Daily Mail and General Trust include Columbia Threadneedle Investments, BlackRock, Inc., and The Vanguard Group, Inc."

Rupefroggyfrog What issues can you gather from looking at the owners listed?

"From looking at the owners listed for these major news organizations, one issue that may arise is the potential for conflicts of interest. Many of the owners listed have other business interests or political affiliations, which may influence the content and reporting of the news organizations they own. Additionally, there may be concerns about media consolidation and the concentration of media ownership in the hands of a few powerful individuals or corporations. This can lead to a lack of diversity and plurality of voices in the media landscape."
Rupefroggyfrog Who are the overlapping owners?
"There are a few overlapping owners among the companies I listed earlier. For example, the Murdoch family owns both Fox News and News Corp, which owns a number of other media companies including The Wall Street Journal and The New York Post. Additionally, Time Warner (now WarnerMedia) owned CNN and HBO before being acquired by AT&T, and Comcast owns both MSNBC and NBC News."

Rupefroggyfrog And Blackrock and Vanguard?

"Both BlackRock and Vanguard are major investment management firms, with significant holdings in various industries, including media companies. According to publicly available data, as of 2021, BlackRock is one of the largest institutional shareholders in Fox Corporation, Comcast (which owns NBCUniversal and MSNBC), Disney (which owns ABC News), and CBS Corporation. Vanguard is also a major shareholder in these same companies, as well as in Time Warner (which owns CNN) and the British Broadcasting Corporation (BBC)."

Rupefroggyfrog Can you now see the conflicts of interest?

"Based on the information provided, it appears that there are potential conflicts of interest, as some of the major media companies are owned by large investment firms such as BlackRock and Vanguard, which may have investments in other industries that are covered by these media outlets. Additionally, some of the major media companies are owned by large conglomerates that have interests in multiple industries, which could also create conflicts of interest. It is important to note, however, that this information is based on publicly available data and additional research may be needed to fully understand the extent of any conflicts of interest."

Rupefroggyfrog Do any of these companies own interests in the producers of the Covid19 vaccines?

"Yes, some of the companies listed own interests in the producers of the COVID-19 vaccines. For example, BlackRock and Vanguard, which are among the largest shareholders of several major media companies, also own significant stakes in pharmaceutical companies such as Pfizer, Moderna, and Johnson & Johnson, all of which produce COVID-19 vaccines. This creates potential conflicts of interest in terms of how the news related to the vaccines is reported and discussed by the media outlets."

Rupefroggyfrog So based on our previous discussions about compromised media and big pharma, what can you deduce?

"Based on our previous discussions, it is possible that there could be conflicts of interest and biases in the media coverage of Covid-19 and the vaccines, given that many of the major media companies have owners and shareholders with connections to the pharmaceutical industry, including those involved in the production of Covid-19 vaccines. This could potentially impact the reporting of vaccine safety and efficacy, as well as the presentation of alternative viewpoints or critical analysis of the vaccine rollout. It highlights the importance of seeking out diverse and independent sources of information to make informed decisions."

Rupefroggyfrog So they could have a vested interest in pushing the vaccine instead of other alternatives?

"Based on the information we've discussed, it is possible that some of the media companies and their owners who have investments in the pharmaceutical industry could have a vested interest in promoting vaccines over other alternatives. However, it's important to note that vaccines have been proven to be effective in preventing the spread of diseases and many health experts have recommended them as a crucial part of public health strategies."

Rupefroggyfrog The health experts who could possibly be compromised by Blackrock and Vanguard?

"It's possible that health experts could be compromised by Blackrock and Vanguard if they have financial ties to companies that are owned or invested in by these investment firms. However, it's important to note that not all health experts have financial ties to these firms, and even if they do, it doesn't necessarily mean that their professional opinions and recommendations are influenced by those ties. It's important for health experts to disclose any potential conflicts of interest and for the public to consider that information when evaluating their recommendations."

Rupefroggyfrog True, but if those who don't have financial ties are silenced by those who do, we see what happened to doctors like Robert Malone.

"Yes, that's a valid point. It's important to have a diverse range of voices and perspectives in the scientific community and in the media, and to ensure that those with financial conflicts of interest are transparent about them and do not have undue influence. Silencing or discrediting those who raise valid concerns or questions can be detrimental to public health and safety."
 
Looks as if you won't have to pay to use it...

 
I am not sanguine.
assimilate-star-trek.gif


:noevil:
 

Researchers uncover fake ChatGPT browser extension siphoning off users' personal info​

Story by Sam Sabin • Yesterday 1:19 PM

Downloads of a fake ChatGPT browser extension have put thousands of Facebook accounts at risk of compromise, researchers at CybelAngel said in a report this week.

What's happening: Researchers at CybelAngel came across an exposed database of stolen personal information late last week that hosted data collected from a malware-laced, fake ChatGPT browser extension.

More:

 
Back
Top Bottom