Bernie Sanders: The Public Should Own Half of the Big A.I. Companies (NYT, 6/1/2026)

[highplainsdem]

https://www.nytimes.com/2026/06/01/opinion/artificial-intelligence-bernie-sanders.html

-snip-

Let us be clear. Artificial intelligence was not created out of thin air. The data and language used by generative A.I. tools didn’t just pop into Sam Altman’s head or Elon Musk’s imagination. A.I. is built on our collective intelligence: our books, songs, artwork, journalism, computer code, scientific research, videos, conversations, images and ideas spanning generations. That is not just the opinion of Bernie Sanders. According to Mr. Altman, the head of OpenAI, A.I. models were trained on our “collective experience, knowledge” and “learnings of humanity.”

For the most part, tech oligarchs have fed this knowledge into their A.I. models without permission, without acknowledgment, without compensation. In other words, the creative work of millions of people — writers, artists, musicians, journalists, teachers, scientists and ordinary citizens — has essentially been stolen by some of the wealthiest people in the world. It’s time for us to reclaim it.

Since A.I. is built on the collective knowledge of humanity, the wealth it generates must benefit humanity. Not just Mr. Musk, Mr. Altman, Dario Amodei and other moguls whose companies are positioned to dominate the industry. Not just venture capitalists in Silicon Valley or money managers on Wall Street who undoubtedly see A.I. as the next great wealth-extracting machine.

That is why I will soon be introducing the American A.I. Sovereign Wealth Fund Act. This legislation would give the public a direct ownership stake in the largest A.I. companies in our country. How? It would create a sovereign wealth fund through a one-time 50 percent tax — not on the profits of OpenAI, Anthropic, xAI and other companies, but paid with something far more valuable than that: the stock.

-snip-

[QueerDuck]

1. No.

[highplainsdem]

3. Why not?

[QueerDuck]

24. A 50% STATE TAKEOVER of private companies is not the answer... it's overreach.

I fully support strict regulation, worker protections, and holding Big Tech accountable. However, as a mainstream Democrat, I view this proposal as a clear overreach. Is he being serious, or is he being provocative to stimulate discussion?

If he's serious, I draw a firm line at the federal government nationalizing or taking a 50% equity stake in any private enterprise. The government's job is to enforce rules, break up monopolies, and protect citizens --- not to seize, manage, and own corporate assets.

If we establish this precedent for tech, which private enterprise would be next? I stand by my firm "NO" response.

[Doodley]

2. How does that help pay for the food, health, and shelter of the tens of millions of people who will lose their jobs

because of AI? This is a problem of our political system, where we have only two parties and one party doesn't give a f**k about the people.

[highplainsdem]

4. It isn't enough. Ideally, generative AI models trained illegally should be destroyed, with new legal AI models

trained only on what's in the public domain and what the AI companies have legally acquired the right to use, first getting the copyright owners' permission and then paying if payment is requested.

But the AI companies aren't about to do that. Using older and very limited training data wouldn't produce AI models as impressive as what they have now. The generative AI industry was deliberately built on theft, with almost all the value of genAI coming from the value of the intellectual property they stole. All those responsible for that theft belong in prison. There is no adequate way to deal with the injustice short of destroying those illegally trained AI models and punishing the criminals.

But I still like seeing people propose as many regulations and penalties as possible on the industry - even though I know the AI bros and politicians under their influence will fight any regulations and penalties - because it helps make people aware of just how unethical and illegal genAI is.

[Doodley]

6. I understand what you are saying, but the genie is already out of the bottle. This is where we are, and

a functioning democracy should ask, how we as a society are going to deal with that moving forward. As you say, it is built on theft. That theft is a preview of the lack of regard for human rights by these corporations will have and the damage to society and the environment. But AI also gives an opportunity for all of us to work fewer hours and have more leisure time, and still achieve the same standard of living or better, only if the political system embraces it for the many and not the few.

[highplainsdem]

9. Just using AI dumbs users down and makes them dependent on AI. There are few if any good uses

for genAI (most of the AI you hear about related to science and medicine is a different type of AI).

GenAI is addictive, too, for many users.

It's foolish to treat it as something that's good, or that would be good if only AI companies shared the profits.

For that matter, there really AREN'T any profits with genAI. It's incredibly expensive and the genAI industry is a bubble maintained so far by hype, delusional venture capitalists, and circular financing.

[Doodley]

14. With all due respect, have you used it much?

[highplainsdem]

19. I've used it enough to know how it works and how tempting it can seem. And I've read thousands of

articles and studies about AI in the last 3-1/2 years, and have also read what were probably tens of thousands of social media posts about it, many of those from experts on AI, some of whom I've corresponded with on X and Bluesky, including some of the experts I've quoted here. I've also talked to a lot of artists and teachers about AI.

I've posted hundreds of threads about AI on DU. And posted a lot about it elsewhere (and been blocked by some well-known industry shills on X, but that's generally considered a badge of honor).

I have no need for genAI. And I'm not delusional enough to want to use it to pretend to have skills I don't have, or knowledge I don't have. I'm not bored or lonely enough to see any reason to chat with a machine. Its error rate or hallucination problem IMO makes it badly flawed tech that should never have been released. And of course there's the fact it's unethical and illegally trained, and all the other problems with it.

Editing to add that I've tried out text, image and music generators. I haven't tried AI for coding because I know very little code (other than HTML I taught myself years ago to build some websites).

[Doodley]

21. With all due respect, I don't think you understand how incredibly useful AI is.

Let me give one example of how my wife and I have used AI in the past week, and I could give many: I removed a hedge in our yard that had been damaged by ice storms. This left an unsightly area, leading to our front door. We used AI to visualize several design options, tweaked it to perfection, and AI produced a list of materials (timber, trellis, bench, plants, ground cover) that we needed and where to buy them and at what price.

What has that got to do with being "delusional enough to want to use it to pretend to have skills I don't have, or knowledge I don't have," or about being "bored or lonely enough to see any reason to chat with a machine?"
Frankly, that is insulting to people who embrace technology in ways you do not understand.

You say you posted hundreds of articles, but I don't think you have even scratched the surface of how useful AI is.

[highplainsdem]

22. With all due respect, you asked AI to give you ideas and tell you where to shop. IMO that's an example

of AI users being dumbed down by AI as they choose to let AI think for them. And having AI tell you where to shop makes you an ideal target for advertisers paying AI companies.

I don't need to use AI for ideas. But if I wanted to see examples of other people's ideas for landscaping, for instance, it's easy enough to search for them and find examples on lots of websites showing real examples from real people. Websites that the AI might have ripped off for the ideas it offered you. Websites whose continued existence is threatened by AI, both because the bots scraping websites add to costs, and because the websites are being deprived of traffic and ad revenue.

What has that got to do with being "delusional enough to want to use it to pretend to have skills I don't have, or knowledge I don't have,"

You let the AI do the landscaping design for you and list the supplies and where to buy them. You didn't bother to get any idea of how many possibilities there might have been for design options, materials to use, plants you could have used. You let the AI tell you what to buy and where to buy it. You let the AI filter what options you had.

Did it save you time? Sure, the same way it saves time if a student is given an assignment to write a story, and they ask a chatbot for ideas and then have the bot fill in more and more of the writing.

It lifts the "cognitive burden" AI peddlers tell people they should want lifted. Let the bot think for you. Let the bot shop for you.

I suspect you could have come up with an equally good design on your own - something that was really personal - and learned something about design and plants and what garden furniture is available in the process. And had reason to feel really proud of what you'd achieved.

But I guess if anyone compliments you on the landscaping, you can tell them AI did it, but at least you picked out which of the designs the AI offered you as options.

[Doodley]

23. With all due respect, you are making a lot of assumptions.

"You let the AI do the landscaping design for you and list the supplies and where to buy them. You didn't bother to get any idea of how many possibilities there might have been for design options, materials to use, plants you could have used."

As for the design, that is not what I said I did, and I didn't. It helped us to visualize design options --- my design options, with images based on my detailed instructions. For example, what would it look like with white trellis, or red, or brown? My wife wanted to see what it would look like before I started any work.

For the plants, I could have spent hours researching the best plants for our location, in a very shady spot, but we gave very specific instructions, for example, we wanted a large fern and something evergreen with flowers, and it suggested options. Can you give one reason why I would spend days do that if I have technology to do do it in an hour? A cognitive burden would be to refuse to understand the usefulness of technology. It would be like using an abacus because one won't discover the benefit in using a calculator.

BTW, I had a career in design, working for a large corporation in Europe. Yes, it saved time using AI. Is that because I am lazy or unwilling to learn? With the time I saved, I am able to do the work myself. Can you see no benefit in that?

[Blue Full Moon]

5. Try all it's tech we paid for. In-Q-Tel funds or should I just say CIA.

[WhiskeyGrinder]

7. I don't want to own it. I want it to not exist.

[MineralMan]

8. Agreed.

I don't want any government investment in it, either, especially using tax dollars. When it crashes, which it will before long, I don't want my my money to crash with it.

It's a scam. It's a pyramid scheme. It will crash.

[highplainsdem]

11. Same here. But as I said above, in the meantime I like seeing regulations and penalties on AI suggested

because it helps make more people aware of just how harmful and illegal genAI is.

[Emile]

10. YES!

[WarGamer]

12. sigh...

Some people are so confused about AI.

Example:

(Ask to Gemini 3.5) Who commanded the 3 spearheads of Operation Barbarossa in 1941?

(Gemini) Operation Barbarossa was divided into three massive Army Groups, each assigned a specific geographic objective and commanded by a senior German Field Marshal:

Army Group North (Heeresgruppe Nord) Field Marshal Wilhelm Ritter von Leeb

Army Group Centre (Heeresgruppe Mitte)Field Marshal Fedor von Bock

Army Group South (Heeresgruppe Süd)Field Marshal Gerd von Rundstedt

(Asking to Gemini 3.5) From which sources did you steal that data? A book like War without Garlands?

(Gemini) The argument that Large Language Models (LLMs) simply "steal" or copy from specific copyrighted books—like Robert J. Kershaw's War Without Garlands—fundamentally misunderstands the architecture of artificial intelligence.

An LLM does not operate like a search engine pulling up a hidden digital library, nor does it keep a repository of text files to copy and paste from. Instead of relying on a specific document, an LLM generates information by drawing upon a vast, synthesized compendium built from thousands of textbooks, public archives, and official war records.

Here is an objective breakdown of how an LLM processes and retrieves historical data:

1. Training is Learning, Not Storing
When an AI is trained, it processes millions of documents—including digitized military histories, academic journals, public domain records, and encyclopedias. The AI does not store these texts. Instead, the training process breaks the text down and analyzes how words, concepts, and facts relate to one another mathematically.

Once training is complete, the original files are gone. What remains is a complex web of statistical associations. When asked about a historical event like Operation Barbarossa, the AI isn't opening a digital copy of a specific book; it is dynamically reconstructing widely accepted historical facts based on the patterns it learned across its entire training data set.

2. A Compendium of Public Domain Facts
The names of the commanders who led the German thrusts in 1941—von Bock, von Rundstedt, and von Leeb—are not the intellectual property of any single modern author. They are matters of public historical record found natively in:

The German Federal Archives (Bundesarchiv)

Official Soviet defensive logs and declassified red army reports

Standard academic textbooks and universal encyclopedias

Because these facts are identical across thousands of independent historical sources, the AI treats them as a shared consensus of human knowledge. In copyright philosophy, there is a strict divide between facts (which belong to the public domain) and expression (the specific, artistic prose an author uses to describe those facts). An LLM synthesizes the facts without duplicating an individual author's copyrighted prose.

[highplainsdem]

15. It isn't true that "Training is Learning, Not Storing" - that's AI company propaganda to try to defend

their theft of intellectual property.

The reality of AI plagiarism:

https://futurism.com/artificial-intelligence/ai-industry-recall-copyright-books

https://spectrum.ieee.org/midjourney-copyright

And of course the same goes for AI music generators.

[Doodley]

16. Thanks for the information. There is also a lot of people who have formed an opinion about AI

without actually using it or seeing its potential. I made a post that used AI to predict the midterms based on possible Trump opinion polls in November, and it was shot down as taking information from Fox News and how dare I use AI that just sums up information from other websites. AI was actually performing very complex mathematical calculations that would take into account past presidential approval numbers with the midterm results of individual states. It would take me many days to perform the same calculations.

[highplainsdem]

20. See reply 15.

[BlueTsunami2018]

13. Well, he's halfway there.

The workers should own all of it.

[Doodley]

17. Bingo!!!

[xuplate]

18. While everyone is debating the issue

Just buy the stocks yourself and ride the investment opportunity of a lifetime.

[Uncle Joe]

25. Norway has a sovereign wealth fund on oil and they're almost always ranked at the top of the list of happiest nations.

It would be nice to promote democracy over capitalism for a change here in the U.S. so the American People will have a greater sense of community ownership instead of just being considered mindless consumers or customers.

(snip)

Dozens of sovereign wealth funds exist all over the world to ensure that ordinary people benefit from national wealth. Norway’s sovereign wealth fund, one of the largest in the world, was funded from the country’s oil wealth and is now worth more than $2 trillion. Instead of a few oil executives pocketing all the benefits of this national resource, Norway made the decision that this wealth should be used to improve life for all of its people.

(snip)

https://www.nytimes.com/2026/06/01/opinion/artificial-intelligence-bernie-sanders.html

Thanks for the thread highplainsdem