Connect with us

Artificial Intelligence

OpenAI and Microsoft negotiations require definition of “artificial general intelligence”

Published

5 hours ago

6 minute read

From The Deep View

Ian Krietzberg

 

OpenAI’s bargaining chip 

A couple of relatively significant stories broke late last week concerning the — seemingly tenuous — partnership between OpenAI and Microsoft.
The background: OpenAI first turned to Microsoft back in 2019, after the startup lost access to Elon Musk’s billions. Microsoft — which has now sunk more than $13 billion into the ChatGPT-maker — has developed a partnership with OpenAI, where Microsoft provides the compute (and the money) and OpenAI gives Microsoft access to its generative technology. OpenAI’s tech, for instance, powers Microsoft’s Copilot.
According to the New York Times, OpenAI CEO Sam Altman last year asked Microsoft for more cash. But Microsoft, concerned about the highly publicized boardroom drama that was rocking the startup, declined.
  • OpenAI recently raised $6.6 billion at a $157 billion valuation. The firm expects to lose around $5 billion this year, and it expects its expenses to skyrocket over the next few years before finally turning a profit in 2029.
  • According to the Times, tensions have been steadily mounting between the two companies over issues of compute and tech-sharing; at the same time, OpenAI, focused on securing more computing power and reducing its enormous expense sheet, has been working for the past year to renegotiate the terms of its partnership with the tech giant.
Microsoft, meanwhile, has been expanding its portfolio of AI startups, recently bringing the bulk of the Inflection team on board in a $650 million deal.
Now, the terms of OpenAI’s latest funding round were somewhat unusual. The investment was predicated on an assurance that OpenAI would transition into a fully for-profit corporation. If the company has not done so within two years, investors can ask for their money back.
According to the Wall Street Journal, an element of the ongoing negotiation between OpenAI and Microsoft has to do with this restructuring, specifically, how Microsoft’s $14 billion investment will transfer into equity in the soon-to-be for-profit company.
  • According to the Journal, both firms have hired investment banks to help advise them on the negotiations; Microsoft is working with Morgan Stanley and OpenAI is working with Goldman Sachs.
  • Amid a number of wrinkles — the fact the OpenAI’s non-profit board will still hold equity in the new corporation; the fact that Altman will be granted equity; the risks of anti-trust scrutiny, depending on the amount of equity Microsoft receives — there is another main factor that the two parties are trying to figure out: what governance rights either company will have once the dust settles.
Here’s where things get really interesting: OpenAI isn’t a normal company. It’s mission is to build a hypothetical artificial general intelligence, a theoretical technology that is pointedly lacking in any sort of universal definition. The general idea here is that it would possess, at least, human-adjacent cognitive capabilities; some researchers don’t think it’ll ever be possible.
There’s a clause in OpenAI’s contract with Microsoft that if OpenAI achieves AGI, Microsoft gets cut off. OpenAI’s “board determines when we’ve attained AGI. Again, by AGI we mean a highly autonomous system that outperforms humans at most economically valuable work. Such a system is excluded from IP licenses and other commercial terms with Microsoft, which only apply to pre-AGI technology.”
To quote from the Times: “the clause was meant to ensure that a company like Microsoft did not misuse this machine of the future, but today, OpenAI executives see it as a path to a better contract, according to a person familiar with the company’s negotiations.”
This is a good example of why the context behind definitions matters so much when discussing anything in this field. There is a definitional problem throughout the field of AI. Many researchers dislike the term “AI” itself; it’s a misnomer — we don’t have an actual artificial intelligence.
The term “intelligence,” is itself vague and open to the interpretation of the developer in question.
And the term “AGI” is as formless as it gets. Unlike physics, for example, where gravity is a known, hard, agreed-upon concept, AGI is theoretical, hypothetical science; further, it is a theory that is bounded by resource limitations and massive limitations in understanding around human cognition, sentience, consciousness and intelligence, and how these all fit together physically.
This doesn’t erase the fact that the labs are trying hard to get there.
But what this environment could allow for is a misplaced, contextually unstable definition of AGI that OpenAI pens as a ticket either out from under Microsoft’s thumb, or as a means of negotiating the contract of Sam Altman’s dreams.
In other words, OpenAI saying it has achieved AGI, doesn’t mean that it has.
As Thomas G. Dietterich, Distinguished Professor Emeritus at Oregon State University said: “I always suspected that the road to achieve AGI was through redefining it.”
Related Topics:

After 15 years as a TV reporter with Global and CBC and as news director of RDTV in Red Deer, Duane set out on his own 2008 as a visual storyteller. During this period, he became fascinated with a burgeoning online world and how it could better serve local communities. This fascination led to Todayville, launched in 2016.

Follow Author

More from this author
Artificial Intelligence / 5 hours ago

OpenAI and Microsoft negotiations require definition of “artificial general intelligence”

Business / 5 days ago

Every week, Canadians are paying a billion dollars in interest payments thanks to federal government overspending

International / 3 weeks ago

Argentina President Javier Milei rejects UN’s ‘socialist’ ‘Pact for the Future’

Artificial Intelligence

AI is another reason why Canada needs to boost the energy supply

Published on October 5, 2024

By

From Resource Works

Massive energy levels are required to keep up with AI innovations, and Canada risks being unable to do that

Artificial Intelligence is already one of the most important technologies of our time, and its development has been pushing innovation at a breakneck pace across huge swathes of the economy. Smart assistants now operate, albeit in a limited fashion, as secretaries for those who need help in the office, while autonomous vehicle capabilities keep improving.

It is a remarkable and world-changing time.

Just as one plays a video game, turns on a light, or starts up their car, AI requires energy. To say that AI’s appetite for energy is ravenous is an understatement, and Canadian governments must understand the challenge that comes with that.

Energy shortages are a growing threat to Canada’s economic security and, yes, our standard of living. Failure to keep up with demand means importing more energy at a cost, or facing energy blackouts, in which case Canada will fall behind in far more than just AI.

New AI models are seemingly rolling out every month, especially in machine learning and generative AI. OpenAI’s ChatGPT and Google’s Bard require huge levels of computing power to work. To train ChatGPT-4, an advanced language model, consumes thousands of megawatt hours of electricity, not incomparable to the energy usage of urban centres.

A single query made to ChatGPT requires ten times the energy of making a search on Google, revealing the massive needs of AI technology. AI is not just another internet search extension or downloadable app, it is an entirely new industry.

AI models are trained and run in data centers, which are central to this energy dilemma. The sheer power consumption in data centers is ballooning, and some estimates warn that the world’s data center energy demand will surge by 160 percent by 2030.

The International Energy Agency (IEA) has reported that AI and data centers already consume 1 to 2 percent of global electricity, a figure expected only to climb as more companies embrace AI-driven technology. As much as AI is driving digital innovation, it is also consuming electricity at a rate we will have to match.

Canada’s energy security is being seriously challenged by rising demand, with or without AI. Historically, Canadians have enjoyed the fruits of abundant, cheap energy generated by hydroelectricity in BC and Quebec, or nuclear power in Ontario. Times, and weather, have unfortunately changed.

A large and growing population, electrifying economies, and the weakening of Canada’s legacy energy sources are pushing the country to its limits regarding power supply.

The current federal government wants Canada to achieve net-zero emissions by 2050, which means that electricity is going to have to double in the next 25 years. Canada is already dealing with electricity shortages, such as in British Columbia, where demand for hydroelectricity is expected to rise 15 percent over the next six years. Manitoba is projecting a shortfall by 2029, while Ontario races to put up new nuclear power plants to avert an energy crisis by 2029 as well.

AI can help Canadians craft solutions to its incoming energy problems as a valuable research aid that can help with modeling and processing data. However, that will mean more energy consumption as part of the rogue wave of energy consumption that AI innovation has created.

As evidenced by the constant developments in AI, it is obvious that the technology is going nowhere, and neither are Canada’s energy shortfalls.

If AI is going to contribute to the surge in energy demand, then it only makes sense that it becomes a vital tool in the search for solutions, and we need those solutions now.

Continue Reading

Artificial Intelligence

Will AI Displace Climate Change As The Next Globalist Bogeyman?

Published on September 26, 2024

By

From the Daily Caller News Foundation

By David Blackmon

On Monday, before most people even knew its annual General Assembly was again invading New York City, the United Nations issued a press release proclaiming the unanimous adoption of what it calls its “Pact for the Future.” Designed to be a successor plan to its “Agenda 2030” — which the international globalist organization admits is failing — the press release boasts that this “Pact” is designed to create a glorious “new global order.”

Where have we heard those dangerous words before?

The U.N.’s alarmist general secretary, life-long socialist Antonio Guterres, had laid the narrative groundwork for Monday’s press release during a preview delivered last week. In that statement, Guterres – who famously proclaimed the world had entered into “the era of global boiling” last July – advocated for a complete restructuring of the world’s “institutions and frameworks” to address major issues like “runaway climate change,” something that no real data indicates is even happening.

In addition to his usual climate alarmism, Guterres also raised questionable alarm about what he termed the “runaway development of new technologies like artificial intelligence.”

“Our institutions simply can’t keep up,” Guterres said. “Crises are interacting and feeding off each other – for example, as digital technologies spread climate disinformation that deepens distrust and fuels polarization. Global institutions and frameworks are today totally inadequate to deal with these complex and even existential challenges.”

In other words, Agenda 2030, the U.N. plan adopted to leverage those institutions to solve all the world’s problems, has failed. The solution? Why, adopt a new “Pact for the Future” to solve all the world’s problems while also rejiggering all those institutions and frameworks. Sure, that will work.

You would think such an all-encompassing Pact approved by a unanimous vote of the world community would make headline news, but that did not really happen. Perhaps that lack of breaking news coverage can be attributed to the fact that a reading of the document itself reveals it doesn’t really offer many plans for specific action items.

Instead, it reads like something written by the talking points compilers for Vice President Kamala Harris’ campaign — a lot of lofty language that doesn’t actually say anything.

Nowhere is this reality starker than in the section on “affordable, reliable, sustainable and modern energy.” After laying out the rationale for pushing the sputtering, subsidized energy transition – as always, painting oil, natural gas and coal as the convenient bogeymen justifying a forced move away from democratic national institutions to change forced by socialist central planning – the document offers only nebulous talking points instead of action items:

  • “Countries can accelerate the transition to an affordable, reliable, and sustainable energy system by investing in renewable energy resources, prioritizing energy efficient practices, and adopting clean energy technologies and infrastructure.”
  • “Businesses can maintain and protect eco-systems and commit to sourcing 100% of operational electricity needs from renewable sources.”
  • “Employers can reduce the internal demand for transport by prioritizing telecommunications and incentivize less energy intensive modes such as train travel over auto and air travel.”
  • “Investors can invest more in sustainable energy services, bringing new technologies to the market quickly from a diverse supplier base.”
  • “You can save electricity by plugging appliances into a power strip and turning them off completely when not in use, including your computer. You can also bike, walk or take public transport to reduce carbon emissions.”

It all amounts to bits of advice, much of which constitutes laudable goals. But there is nothing new here, nor is there anything that is going to lead to meeting the UN-invented “net zero by 2050” target. The simple reality is that demand growth for energy – real, 24/7 energy – will continue to outstrip the ability of global or national governments to force reductions in carbon emissions, because modern life is not sustainable without the use of carbon-based energy. Period.

By citing the evolution of energy-hungry AI technology as a development to be feared and attacked, Guterres admits this reality. He also appears to be admitting that the attempt to displace democratic institutions with socialism using climate alarmism as the justification is also failing, thus necessitating the need for a different bogeyman.

It is all so incredibly tiresome and unproductive.

David Blackmon is an energy writer and consultant based in Texas. He spent 40 years in the oil and gas business, where he specialized in public policy and communications.

Continue Reading

Trending

X