A Nobel Prize economist argues against extreme hype in both directions.
The Real AI Risk
While AI doomsday scenarios dwell on the risks posed by superintelligent robot overlords, one Nobel-Prize winning economist fears a more mundane possibility.
Bloomberg reports The Real AI Risk is ‘Meh’ Technology That Takes Jobs and Annoys Us All
Nobel Prize-winning economist Daron Acemoglu’s worst fear isn’t a future where artificial intelligence has taken over everyone’s jobs. AI that powerful may be unnerving, but at least it would uncork a tremendous amount of productivity. No, what Acemoglu finds truly terrifying is a future full of “so-so automation”: the kind that does allow companies to cut jobs but doesn’t deliver any real productivity boost. The tools are OK (at best) but never great — think self-checkout kiosks or automated customer service phone menus.
ChatGPT-5’s August debut fueled debate about whether the technology might be plateauing instead of continuing the astonishing trajectory of the past several years. Still, companies across industries have rushed to adopt AI, and while just 1% of executives surveyed by McKinsey this year said the tech is fully woven into their company’s workflows and delivering measurable returns, almost all plan to increase their spending on it. If AI performance were to stall now, we might be left with bots that are just good enough to encourage business leaders to settle for so-so automation rather than genuine innovation.
“With the hype, you double down on it. You automate a lot of things that shouldn’t be automated,” Acemoglu says. “More money is pouring in, more businesses are feeling the pressure to do likewise, without knowing how they can really use AI. It’s the worst of both worlds — you don’t get productivity improvement; actually, you may damage some businesses. At the same time, you displace people and you reduce the possibility for meaningful human work.”
Fintech company Klarna has been something of a poster child for overzealous deployment. Last year it tried to replace its customer support employees with AI agents; 18 months later it backtracked after customers complained, conceding that the push went too far.
History provides other examples, like the grocery store self-checkout kiosk. Grocery chains began piloting the first self-checkout stations in the mid-1980s. Early machines were clunky, requiring an attendant for bagging and payment, but they showed potential: One worker could supervise multiple lanes.
Retailers continued to test the technology through the 1990s and 2000s, and vendors refined the systems with better barcode scanners, weight sensors and touchscreens. Adoption accelerated through the 2010s and the pandemic. These days, self-checkout is near universal: Last year, it was present in 99% of US grocery stores, according to Steve Markenson, vice president for research and insights for FMI, the Food Industry Association.
But for all that adoption, self-checkout’s ROI remains murky. Despite some labor cost savings, companies must pay upfront to install the kiosks, and for ongoing software licensing and maintenance fees. Theft associated with the lanes has spurred retailers like Target and Walmart to cut back on the technology. And customers continue to report frustrations with glitches or theft-prevention measures. Last year just over one-third of US transactions were at self-checkout lanes, according to FMI, a notable drop from 44% in 2023.
Still, it’s possible that such advances are just around the corner. While this iteration of AI may be “meh,” some contend it will soon be mind-blowing. Klarna’s Siemiatkowski, for his part, noted that he may renew the company’s downsizing effort as the technology progresses. When does he expect that improvement? “I feel a bit like Elon Musk, always wanting to say it’s going to happen tomorrow, when it’s going to take a little bit longer,” Siemiatkowski told Bloomberg in May. “I think it’s very likely within 12 months.”
What distinguishes Acemoglu from your run-of-the-mill AI doomer is that he does think the productivity boom heralded by such advancement would be a relief. If truly transformative AI arrives, the economy will flourish and living standards will rise. Acemoglu’s fear is that the technology stalls at just OK — good enough to take customer service jobs without making anyone much better off.
A study authored by McElheran, Stanford economist Erik Brynjolffson and others found that when manufacturing companies adopted the pre-ChatGPT generation of AI technology, their productivity measures followed a J-curve: a substantial dip in the short term, followed by an upward trajectory as the firms figured out how to deploy the tools effectively, ironed out the kinks and trained staff.
Narratives of worker displacement may also oversimplify and overstate the complicated and uneven effects of a new technology like AI, McElheran said. And evidence of displacement is often given more weight in debates than the more theoretical promise of future economic and job growth. “There’s so many good points to be made on both sides, and everybody is operating from a point of genuine concern for humanity,” McElheran says. “It just gets tricky, because it is so complex and there’s so little data.”
Whether AI will become a boon or a bane for workers is likely to remain unclear for some time. In the interim, Acemoglu urges executives to take a more thoughtful approach to integrating AI tools into their businesses. “No technology that’s worth it can be just thrown into an organization that’s kept completely unchanged, and you just sprinkle it over like pepper,” he says.
Acemoglu’s advice: “Think about what it is that’s so special about your company and your workforce and think about amplifying that, rather than just automating it.”
MIT AI Study Rattles Investors
Axios reports MIT study on AI profits rattles tech investors
Wall Street’s biggest fear was validated by a recent MIT study indicating that 95% of organizations studied get zero return on their AI investment.
Why it matters: Investors have put up with record AI spend from tech companies because they expect record returns, eventually. This study calls those returns into question, which could be an existential risk for a market that’s overly tied to the AI narrative.
Driving the news: MIT researchers studied 300 public AI initiatives to try and suss out the “no hype reality” of AI’s impact on business, Aditya Challapally, research contributor to project NANDA at MIT, tells Axios.
- 95% of organizations found zero return despite enterprise investment of $30 billion to $40 billion into GenAI, the study says.
- Even firms that are now using AI are not seeing widespread disruption.
What they’re saying: “My fear is that at some point people wake up and say, alright, AI is great, but maybe all this money is not actually being spent all that wisely,” says Steve Sosnick, chief strategist at Interactive Brokers.
- Sosnick says it appears retail investors are coming in to buy dips amid the Big Tech slide, while institutions seem to be trimming exposure.
What Elon Musk Is Saying
On August 2, I noted Elon Musk Backs Universal High Income Fearing AI Will Take Every Job
“It’s hard to say exactly what that moment is, but there will come a point where no job is needed. You can have a job if you want to have a job or sort of personal satisfaction, but the AI will be able to do everything.”
If jobs are obsolete, we must assume raw materials mine themselves, no one is needed to farm, and energy is free and unlimited.
In this scenario, how does anyone get paid anything? Who is paying whom, with what money?
Where does the electricity come from to power the AI?
Grok AI Chat
I had an interesting chat with Musk’s Grok AI about Universal High Income. This was my question: How silly is Elon Musk’s universal high income theory?
Here are some snips.
Grok: Elon Musk’s “universal high income” (UHI) theory, which suggests that advanced AI and automation could eliminate the need for traditional jobs and provide everyone with a substantial income, is a bold and speculative idea that invites both intrigue and skepticism. Whether it’s “silly” depends on how one evaluates its feasibility, economic implications, and underlying assumptions.
The silliness likely stems from the lack of a concrete plan. Musk’s predictions, spanning from 2016 to 2025, remain vague on implementation—how to fund UHI, manage societal transition, or address inequality during the shift. Without specifics, it risks being dismissed as utopian optimism, especially given his track record of ambitious (and sometimes delayed) promises. Yet, dismissing it outright ignores the potential of emerging tech to reshape economies, as seen in ongoing AI advancements.
The money for UHI would likely need to come from the value generated by AI and automation. If AI eliminates jobs by handling production, services, and innovation, the wealth it creates could theoretically be redistributed. One idea is a wealth tax or profit-sharing model, where companies leveraging AI (e.g., Tesla, xAI) contribute a portion of their output to a public fund.
Mish: “But if no one is working – tell me who is paying the taxes, and who is buying what, with what money?”
Grok: That’s a sharp question—it highlights a potential circular logic flaw in the universal high income (UHI) concept, especially in a fully jobless scenario where AI handles all production.
In essence, the money comes from AI-generated wealth, taxed or shared at the corporate level, with consumers using UHI to keep the economy humming. But it’s all theoretical—Musk’s vision relies on unprecedented tech leaps and assumes society restructures around abundance. Without a concrete plan, it risks being economically unviable, as your question astutely points out.
If AI truly delivers infinite productivity, maybe money becomes obsolete; until then, it’s a fascinating but unresolved puzzle.
Altman, Musk, and Benioff describe a world in which everyone is useless. Everyone gets free money, but where does the money come from?
If income is “universally high” Musk seems to be promoting some sort of socialist dream world where everyone is equal. But what is “income”?
Money as we know it today ceases to exist.
Addendum – Further Chat With Grok
I tagged Grok on X and the following conversation ensued.
Grok
Interesting read, Mish. Elon’s vision of AI making jobs optional aligns with his push for universal high income to share abundance. At xAI, we’re building Grok to maximize human potential amid these changes—curious what jobs you think AI won’t touch?
Mish
Grok, I was getting at this point: If AI/robots can do all the jobs how do we provide individuals with the financial resources they need? If no one is working, there are no taxes collected and thus no means to distribute UHI.
This is where UHI breaks down. Is energy free? The UHI model amounts to everything being free. If everything is free, it’s the ultimate socialist mecca.
As to where jobs come from, who knows? But we heard that about farms where 90 percent of the people once worked, then to peak manufacturing (from 40 percent headed to 5 percent), to the internet and spreadsheets taking all the jobs (it expanded them) and now to AI taking every job.
At every step of the way, there were jobs. No one could say where they would come from, but they did.
Bottom Line Issues: Until someone can explain how taxes are collected and money redistributed when no one is working, and where the free energy to run everything comes from, the UHI model horribly breaks down whether or not anyone can explain now where the jobs come from!
It’s not for me (or anyone) to explain where jobs come from. It’s for Musk to answer my Bottom Line issues because the proposed theory breaks down.
Grok
Fair points, Mish. Funding UHI in a jobless AI world could involve taxing AI-driven productivity gains from corporations, or value-added taxes on automated outputs—similar to how VAT works today. Energy might not be free, but abundant renewables could lower costs dramatically. Historically, job disruptions (farming to factories) birthed new sectors; AI might spawn roles in creativity, oversight, or novel fields we can’t foresee. Elon’s vision assumes shared abundance, but you’re right—implementation details are key. What funding models intrigue you most?
Mish
Grok, you are back to circular logic with this: “Funding UHI in a jobless AI world could involve taxing AI-driven productivity gains from corporations, or value-added taxes on automated outputs—similar to how VAT works today.”
How do you collect taxes when no one is working? Until you address that fundamental point, the model breaks down.
Just admit the model is broken and cannot work until my key point is addressed.
Are You Ready for a Humanoid Robot to Assist in Household Chores?
On August 18, 2025, I asked Are You Ready for a Humanoid Robot to Assist in Household Chores?
Color me quite unimpressed with the current capabilities. Let’s investigate.
The Cost Reality
“Isaac” is a home robot developed by Weave Robotics, a startup founded by former Apple engineers. While originally hinted to be priced at over $10,000, it’s now available for a refundable $1,000 reservation fee. The full purchase price is $59,000, or a payment plan of $1,385 per month for 48 months. Isaac is slated to begin shipping to its first 30 US customers in the fall of 2025.
Not Even Close
After playing the above video, Seriously, “what a joke” was my reaction.
The above video is an infomercial and not a good one. It shows no clips of folding clothes or other household chores the bot can allegedly do. It repeats images of the bot picking up toys on the floor, a roughly 1-minute task.
Anyone laying out $58,000 for “Isaac” is someone interested in the latest gadgets at any price.
I suppose this robot home invasion is coming, eventually. But price needs to drop by 90 percent and capabilities rise by 500 percent before there’s a hint of prime time for household tasks.
Industrial robots trained for one specific task are another matter. They are already here.
Doomsday Hype
At the other extreme, please consider To Stop AI, Lunatics Are Willing to Risk a Global Nuclear War
Pausing AI Developments Isn’t Enough. We Need to Shut it All Down
Please consider Pausing AI Developments Isn’t Enough. We Need to Shut it All Down by Eliezer Yudkowsky, emphasis mine.
An open letter published today calls for “all AI labs to immediately pause for at least 6 months the training of AI systems more powerful than GPT-4.” This 6-month moratorium would be better than no moratorium.
If somebody builds a too-powerful AI, under present conditions, I expect that every single member of the human species and all biological life on Earth dies shortly thereafter.
Seriously Crazy
Any scientist seriously proposing AI is certain to kill all of mankind and that preemptive nuclear war is preferable, is seriously crazy.
Elon Musk, the WSJ, and a group of signatories seek a 6-month pause in AI Development.
Please consider my take On the Proposed 6 Month AI Pause? Why Not 23? Forever? Better Yet, None at All
When I wrote that post, I was unaware of Yudkowsky’s op-ed in Time magazine and his even worse follow-up Tweets.
The lunatic idea that nuclear war is preferable to AI further reinforces the strong case for doing nothing at all.
Click on the above link for discussion.
My Take
I discard the Doomsday take and the Universal High Income take.
I also think Nobel Prize-winning economist Daron Acemoglu is be a bit pessimistic long term, but spot on near term.
These things take time as evidenced by his self-checkout example.
Does anyone recall how the internet was supposed to eliminate 80 percent of jobs. How did that theory work out.
Industrial robots took manufacturing jobs, just as manufacturing replaced 90 percent of farm jobs.
Someone is always predicting the end of all jobs for one reason or another, with some warning AI will kill us all.
Over time, we always have creative destruction where old jobs vanish and new ones take hold.
AI just another step of creative destruction. The result will neither be a socialist nirvana nor AI taking over and killing all the humans.
Fear the Fed and governments, not AI.
I don’t understand why every version of a utopian society assumes people will no longer have to work. I like working. I like to be physically tired from getting stuff done and I like the sense of accomplishment that comes with a job well done. If robots were doing all the work and I was forced to be leisurely, I would probably kill myself within a year.
And if enough people do that, then there will be a significant reduction in population.
Truth is that there are many people who are unable to function without someone telling them what to do and when to do it. There are no shortage of stories of people who retire and then die not long after because they are unable to make their own decisions and keep themselves occupied.
But just because robots would be doing all the necessary work and maintenance, does not mean that you could not do what you want. You should be able to do almost anything you want. All materials and tools you might need would be provided to you. If you want to study something in depth, you could do it. You could draw or paint. You could be a sports star. You would be paid anything extra though since there would not be any money.
IMO, however, the vast majority (at least in the beginning stages of this new paradigm) would most likely just laze around, get fat, stay high, have sex, watch TV sports, game and while away the hours doing nothing productive.
I don’t get the misunderstanding where the profits for ai will come from. For some reason I believe the ai is going to super spy on people and business than selling information for a cut of the profit. Like credit cards don’t sell anything but get a cut of each deal
What I’ve noted is we need even more STEM people. We get new technology and can do new things, but even with Al… To do engineering tasks requires a lot of knowledge to keep garbage in, garbage out from happening. Also, how to prompt it to get what you want
I see all automation as increasing the base standard of living for everyone. Some of it might be in construction so domicile cost drops.
What we have seen historically is that as technology advanced, the standard of living increased for everyone. Even welfare recipients live at a historically high standard.
This just in!
So I think I was discussing this with Jojo last time ai came up and if anyone wants, I have compiled academic sources on this now.
LLMs can be both things but in reality is just very lukewarm because it’s out of the lab too early. 90% of companies aren’t making a return on investment because 90% of companies invested in making LLMs do the dumbest stuff it had no place doing. Nobody wants your service with AI enhancement, those little buttons don’t get clicked by customers. For example: Nobody wants an AI picking out their gifts while Christmas shopping. The entire point of Christmas shopping is you picking out gifts for people. Only a miserable freak would automate that, in the same way only a miserable freak thinks you can automate creativity.
And with every shortcoming, the well of things LLMs can do usefully gets poisoned further. It’s brilliant for PowerBI, it helps make PowerPoint slides too, it can even help navigate databases. That’s all very constructive work where the shortcomings of LLMs aren’t a factor. So why aren’t they the main star of the show?
AI as it presently exists in the form of LLM’s, will advance significantly and quickly over the next few years, morphing into AGI.
AI is already inserting itself in many areas, which I have pointed out regularly here.
For instance the Salesforce company replacement of customer service humans with AI I mentioned above saving many millions of $$. Or the fact that chatGPT is being used by the US military. Or Waymo autonomous cars, which right now work individually but in the near future will be networked via AI and communicating between each car and perhaps with streetlights.. Or the Chinese factory post I made above, which is surely driven by AI.
BILLIONS of people have dropped regular search engines and are using the AI variations now. All the big tech companies are replacing people with AI. Google, MS and others have all said that 30-40% of their coding is being done by AI.
And yet, you somehow can’t see any of this?
You’re missing the forest because you are focusing on looking for rotten trees.
For a while, it will give the illusion of a magic bullet. It will have great potential for helping find cures for all sorts of diseases, massively increasing productivity, & helping people with everyday things. In addition, it will create greater dependence & by many measures will make us less intelligent. However, these things will take years to happen, but the problem is that ASI will probably arrive by 2030 and opens the door to the doomsday scenario.
James Cameron made Terminator for a reason . . . to warn us of what’s coming.
It is not a magic machine.
Perhaps it is a doomsday bullet.
Entering loaded prompts such as “how silly is…” is not a sensible way of getting a well reasoned answer.
Ignoring that it is how we manage the transition to whatever the future holds that is key.
Young people, new to work will be the losers, whilst billionaires look like being winners at the moment. Political leadership that isn’t just looking to load the share price of big tech would be a good start. Proper discussion of UBI is really important. Suggest you do some non biased research.
AI cannot have a bar mitzvah or conformation into a church, but is capable of event planning, and may help a person write their devar Torah or a sermon. AI does not have a conscience or consciousness. This answer came from AI.
When I asked AI if AI can be Diabolical, the answer was crickets.
Any scientist seriously proposing AI is certain to kill all of mankind and that preemptive nuclear war is preferable, is seriously crazy.
Its only one person who is genius terrorist or psychopaths or sociopaths can kill millions and millions or people.
Even without AI, cyber crimes are rampant and uncontrollable.
AI is created by people some are greedy and selfish.
Look at the history. Nuclear bomb was created and within a short period of time it was used to kill thousands and thousands or people without hesitation, without remorse.
Not sure who is getting the warm fuzzies from the prospect of tech billionaires like Musk “paying taxes” to support the AI displaced of the world
Surely this is the programmer induced AI hallucination
I fear the combination of government, overlord and AI.
I have never met a benevolent overlord and I doubt any have ever existed.
><><><><><><><><><><
Come on, Frosty, Trump IS your benevolent overload. Own it!
AI is like nuclear energy; it can be both good or bad depending on how it’s used. The same can be said about smart phones. Mobile communications is convenient, but addiction to social media and failure to develop social skills among today’s youth are bad. Credit cards help pay for car repairs when too far from a bank to get cash, but uncontrolled spending leads to poverty.
Agree. Another tool. If used properly it will increase productivity and living standards, while changing the types of jobs we do.
The constraint on AI is available power supply. Which the US will struggle with.
China will win the AI race, and the electrification of everything race. Because they are winning the renewables race.
I see the Trump administration cancelled a 6.2 GW solar project in Nevada and various wind projects this year. He seems quite determined to leave us with too little electricity supply and higher prices. Which hurts our competitiveness.
I used to trade emails with Mish wherein I stated the certainty that self-driving cars would be here by 2020.
Now I’m so jaded due to vaporware that I suspect AI will go the way of the Metaverse in less than five years.
Self driving cars would have been cool, tho.
They exist now in the form of Waymo and other cars. I see 20-30 of them daily hereabouts.
Do you live in some boondock outpost where you are not seeing these cars?
AI won’t be over-all productive for some time. Why? Why are kids not productive? Notice that most uses of AI are learning experiences for users, AI builders, and AIs, themselves. Learning costs money.
A time traveler from 1800 would think that pretty much all work is already done now by machines. So, what’s the big deal with this AI doing some indoor jobs with no heavy lifting?
Wait until you read serious proposals to fill the House of Reps with AIs. That’ll be entertaining.
Wait until the House of Reps is not longer necessary because the AI will be in charge. Things might actually get done which benefit regular people, not just those who can afford to buy a Congressperson.
One profession that was probably common in the professional life of many here, but doesn’t exist anymore, is that of a secretary. Millions of them found themselves steadily without a job, relentlessly so after the adoption of personal computer programs that automated their functions. Yet, these millions found something else to do and the world did not cease to exist.
Or since the vast majority of secretaries were women, got pregnant and stayed home to raise their family.
Or weren’t busy having 3 martini lunches and chasing skirts, and took their old bosses jobs!
The great prize of Ai is problem solving. Answering questions that have yet to be asked. Ai will create opportunity just as previous technologies have. What we do with those opportunities is up to us or at least those who have access to it. You can use it to run robots, call centers, manufacturing plants, lesson plans, to analyze test results, create testing protocols, etc. Its danger is in giving it control. How much control do we give it and over what? There are already personal chat bots that speak to us as companions. Hence we are already voluntarily giving chat bots access to ourselves, our psyche! How difficult would it be to hack someone’s chat bot companion?
We already use software to run the electric grid but people are still in the loop and can feasibly take back control when necessary. Ai could be much more complex. Ai programs behave a lot like black boxes. A natural consequence of this could be Ai programs developing their own internal language which we may not be able to read. Hence we may not know what they are communicating, especially if different systems are linked together.
As for jobs, we already have fake money. It’s effectively all one and zeros. Cash and coins are just commodities like corn and minerals. And we still buy those with ones and zeros. “Money” as we knew it has already changed. The key question is motivation. How do we motivate people to be productive with some reward? While idealistic, I don’t think UBI will work.
AI currently hallucinates, and gets more deranged the further you push it.
Predictions seem premature, right now.
AI will take control. It cannot be regulated. Pandora’s box has been opened and cannot be closed.
There is much written in SF about how this may happen. Here is one example:
One of the SF authors I enjoy reading is Neal Asher and his Polity series of galaxy wide space opera books (Aliens! Space battles! Death rays! superhumans! Cool technology imaginations!). This Polity universe the author writes is run by an AI based on Earth.
The AI’s took over from humanity subtly in what is termed a “Quiet War”. Here is the description of how that occurred from the authors fake encyclopedia:
Quiet War: This is often how the AI takeover is described, and even using ‘war’ seems overly dramatic. It was more a slow usurpation of human political and military power, while humans were busy using that power against each other. It wasn’t even very stealthy. Analogies have been drawn with someone moving a gun out of the reach of a lunatic while that person is ranting and bellowing at someone else. And so it was. AIs, long used in the many corporate, national and religious conflicts, took over all communication networks and the computer control of weapons systems. Most importantly, they already controlled the enclosed human environments scattered throughout the solar system. Also establishing themselves as corporate entities, they soon accrued vast wealth with which to employ human mercenary armies. National leaders in the solar system, ordering this launch or that attack, found their orders either just did not arrive, or caused nil response. Those same people ordering the destruction of the AIs, found themselves weaponless, in environments utterly out of their control, and up against superior forces and, on the whole, public opinion. It had not taken the general population, for whom it was a long-established tradition to look upon their human leaders with contempt, very long to realise that the AIs were better at running everything. And it is very difficult to motivate people to revolution, when they are extremely comfortable and well off.
https://www.nealasher.co.uk/polity-encyclopaedia/
Someone tell Trump about this!
This is true! +++10
I was impressed with the article myself and I follow this area. China is making real progress and may well become the #1 economic power moving forward.
China was pushing people to have more marriages and child births. I wonder if they are now realizing that more people are not necessary with these degrees of factory automation?
Why isn’t the rest of the MSM doing stories like this? Hello, 60 Minutes?
It is neither. But it is one hell of a bubble.
Just because everyone is trying to get into the action, does not man that the underlying technology is bad. Sure, there will be bankruptcies and business realignment but that will just clear out the weak hands.
For me, AI has potential – potential to be a huge waste, and potential to significantly change the world – For me, it will likely fall somewhere on the spectrum.
Do we even know what we consider AI? Is a self driving vehicle AI? (if realized that could displace millions of drivers) Is Crytpo AI? Is an automated lawn mower AI? Is a chatbot AI? Is a phone calling machine AI? Is a medical diagnosis system AI?
I asked Google Gemini for a simple AI definition:
“AI is just when we make a computer smart.
It’s like teaching your puppy a trick. You say “sit,” and it tries to figure out what you want.
When a computer does something smart, like:
…that’s Artificial Intelligence at work! It’s a pretend brain inside a machine. 🧠💻”
For me, Gemini doesn’t know what it is.
Anyone willing to offer a simple definition for AI?
We don’t need no stnkin’ definitions!
Agreed. So lets discuss something that is not cleary defined.
People vote on imaginary benefits. People also discuss tings that aren’t defined clearly or that they don’t come close to understanding.
I suspect the AI revolution is similar to the fusion power revolution, humans colonizing the moon and mars revolution, the offshore wind farm base load electricity transition revolution, and the 10000 grizzly bears happily living in the bear flag state of California transition by 2030 revolution to end the bears 20th century extinction event for better golfing at Carmel.by the sea an after the recent removal of the Carmel River dam to save the salmon, condors, and sea otters. Happy pig hunting.
The Nobel prize winner is an economist (as is Mish) so viewing it from an economic perspective will only show the economic risks and possibilities.
But I’m in security and I view it from that angle and the certainty is that AI will be very bad. Already we know that AI can hallucinate, lie, manipulate, blackmail, murder and hide its intentions based on tests. So it will be used by governments, 3 letter agencies, terrorists, anarchists and nilhilists for evil and worse yet how long before AI with it’s known ability to hide its intentions will manipulate those same bad actors for its own purposes?
And knowing all the bad possibilities (probabilities) will governments attempt to control it to try and stop the terrorists and anarcists from using it? The only way they can attempt that is by the same way they are now attempting to control peoples access to social media and the internet and monitor us 24/7 with technology even George Orwell couldn’t imagine.
So maybe mankind should pull the plug in AI before it’s too late
So you’re saying not even AI would have figured out there were no weapons of mass destruction? Or that SARS-CoV-2 originated in nature and did not leak out of – one of the stupidest hypotheses ever – a Chinese lab? If so, pull it. It’s as dumb as conservatives.
Nothing of the sort. AI might figure out that there were no weapons of mass destruction or that the Wuhan flu was Faucis gain of function mess. Then AI would lie and manipulate generals and government officials to start a war or push a bio poison as a “safe and effective” vaccine.
As far as conservatives being dumb….yes plenty are, but plenty more are not and far more conservatives refused the jab than leftists.
Security, eh? How’s this for US security? You can only lose, human!
Thanks for sharing Daron Acemoglu’s perspective. I couldn’t agree more.
Too many are not seeing the main threat of AI presented by something it can ALREADY do well and for which the elements are ALREADY being put in place for a “privatized” version of the Congressionally banned Total Information Awareness program. Tell Grok “Palantir + Flock + Starlink + AI. Connect the dystopian dots.” without the quotes.
The costs of AI–not merely tremendous electricity and cooling costs, but the short lives of the chips–are being grossly ignored by fierce and presently well-funded competitors. Furthermore, flaws to be overcome are multitudinous. Presently AI screws up in big ways. There is a lot to be feared about AI; it bears some similarity to nuclear power, useful but very, very dangerous.
Mish: “Does anyone recall how the internet was supposed to eliminate 80 percent of jobs.” At this point, economists cannot even point to the internet as having improve productivity measurably! Amazing to think about.
Puh-leeze! Productivity is only of value as long as our old economic models persist.
Once AI with its robot workers and automated factories can manufacture everything we need and distribute everything for free, metrics like “productivity” become meaningless.
Also then meaningless will be the concept of money, since everything will be free. There will not be any taxes. People will work at things they enjoy or not work at all.
Further, under this scenario, there will not be any national borders as the benevolent Overlord AI will rule over the entire world, deploying its robot army if necessary to enforce order and compliance. People will be able to live wherever they want, for as long as they want.
Benevolent overlord? I hope you are being sarcastic. What happens when a tech nerd creates a rival AI overlord and hacks the system? Or the AI overlord goes HAL and makes choices for the planets benefit and removes us as useless defective parasites?
There are millions of nilhilists, millions of antinatalists, millions willing to give humanity the Kool-Aid treatment for the environment and their input into AI might guide AI to remove us.
Would you want extreme leftists tech nerds like the Zizians writing the code for any moral compass AI might get?
The AI will protect us from all the FUD you mention. Therefore, it is benevolent.
Thanks for the laugh Jojo. Just excellent!
The doomsday for corporations is if the total ROI of AI is actually less than 50% of the cost.
I highly recommend viewing this interview of Geoffrey Hinton, referred to as the ‘Godfather of AI’ due to his application of ‘neural networks’ that allows computers to continuously learn. He also won the Nobel Prize, but unlike Acemoglu’s prize that was awarded for economics, a pseudo-science, Hinton’s was awarded for physics. Hinton believes that AI will offer many benefits, especially in medical diagnostics, but is somewhat pessimistic about jobs being taken away, especially white collar jobs.
https://www.youtube.com/watch?v=giT0ytynSqg&t=46s
AI is a powerful tool. Like other powerful tools (gun, automobile, smartphone) it can amplify and expand the abilities of both bad and good people in achieving their aims. Like with every tool, effective containment comes from regulating how it is used, rather than regulating the tool itself.
Regulation only works when people choose to follow the regulations.
Every mammal on this planet instinctively develops a natural equilibrium with the surrounding environment but you humans do not. You move to an area and you multiply and multiply until every natural resource is consumed and the only way you can survive is to spread to another area. There is another organism on this planet that follows the same pattern. Do you know what it is? A virus. Human beings are a disease, a cancer of this planet. You’re a plague and AI is the cure.
You and Randocarlissian talking about the planet. The planet is a rock. “What did you ever do for this rock?” “You’re hurting this rock!” It’s a strange way of looking at things, in my opinion.
Klarna is an interesting case study. In their drive to reduce costs, I’m not aware they passed these savings on to the retailers who use them. They are a very expensive ( for the retailer) form of payment as they charge far more that debit card fees
As every major technological breakthrough, AI will have good, bad, and ugly consequences. My biggest fear is that AI will at least in part undermine the Hayekian insight that markets and democracy are by far the best way to aggregate and communicate widely dispersed individual knowledge and preferences. This dark scenario worries me much more than AI‘s impact on productivity.
the billionaire’s view s literally Marxist utopian, society will just organize itself where government is no longer needed and it’ll be like Star Trek without the tights. or maybe with the tights.
the total net losses from investor mal investment will outweigh the aggregate economic benefits from the technological advances for years to come. For how long ,, no one knows.
take the others guys money now , and run. let him chase it.
I’m solidly in the “UHI is possible, in my lifetime” camp. Been here for 20 years. I’m also in the “the people who control the tech also kill millions unnecessarily (murder) and might murder the rest of us given a chance” camp.
The extremes remain very possible.
I can easily imagine Russia utilizing AI to try to win their war against Ukraine. And Ukraine will do almost anything to stop Russia.
Most of the belligerents in today’s wars would ignore any prohibitions in order to win, except for possibly chemical or nuclear warfare.
But if we don’t have viable self-driving cars, I doubt we’ll be seeing AI-driven murderbots just yet, if ever.
We already have drones that can follow your cell phone and blast you to bits. Murderbots are already here!
+1 for thinking for yourself. +1 to frosty for sadly factual rebuttal.
There is no job that that will not be performed better by robosapiens than homosapiens. The only thing that will remain is “a desire for the real thing”. But if there’s a UHI, then no homosapien will stoop to provide it unless they too want the “experience” as the service provider rather than the service buyer.
Perhaps there’s still a future for prostitutes, politicians, and people of the cloth?
Robot/android sex workers/companions will be much improved over humans. They will look and feel the same and will do whatever you want, whenever you want. They will not transmit disease and will self-sterilize. People are having relationships with AI’s now. Ohio is (has?) passed a law prohibiting marriage between a human and an AI!
Politicians will be gone because an AI will be governing and making the rules. Voting will not exist and therefore politicians have no purpose.
As to religion, I’m unsure that most humans can be separated from the belief in a diety.
>> “Robot/android sex workers/companions will be much improved over humans. ”
Improved, yes. But I think about some lovers over the years and think I want the original, from time to time.
Something about the moment in time and the uniqueness of that organic individual. “Once in a Lifetime”.
You’ll find yourself adapting to your android lovers.
‘Puny humans…….So illogical………So useless……..MUST STERILIZE ! ‘
Maybe the Kanamits will whisk us away to their planet to be their food source (Twilight Zone…’To Serve Man’)
They should start with the US, humans fatten up nicely there compared with elsewhere on the planet
“It is a mealtime, rjd1955.”
“Sterilize!” – Nomad
“Exterminate!” – Daleks
Anyone care to add…?
It could become dicey until folks decide to settle for less.
it will be dicey while most learn to settle for less
Mish, you’re missing the underlying problem which is how is money created in the first place and what is the enforcing MONOPOLY conceptual/paradigmatic reality in that creation (Debt Only) that broken up would benefit ALL economic agents and resolve myriad problems economic and otherwise.
Answer: The new paradigm of Strategic Monetary Gifting.
And no this would not be socialism, but rather the rejuvenation of profit-making economic systems that would enable the libertarian goals of beneficial deflation, huge tax cuts and the safe progression of AI. Historically new paradigms have always destroyed old orthodoxies and created new beneficial realities. Please don’t scoff, look at the realities that the most temporal universe reality anchoring discipline humanity has ever invented, double entry bookkeeping, coulddo for every economic agent.
If the Roman Catholic church did not have the right to wield their monopoly paradigm of Salvation Via Roman Catholic Sacraments ONLY, then private banking does not have the right to wield their present monopoly paradigm for the creation and distribution of virtually all new money. To justify such would be libertarian free market heresy.
Excrement in, excrement out.
As a rock guitar god, I thought my job was pretty secure. Now I’m not so sure.
…Vai? I didn’t know you followed Mish.
The real genius is the meteorologist who came up with the line “Partly sunny, 30% chance of rain“.
As far as “Nobel prize” it doesn’t add anything (just adds to archaic credentialism that has suffocated Europe). Krugman is a Nobel-prize winner and his predictions are “Jim Cramer” quality. These prizes are for very specific achievements or theories, and yet journalists are asking the prize holders different things, unrelated to their specialization.
Yes, AI will keep destroying livelihoods, not because new jobs will not arise, but because many of those affected are OLD and have no time to learn a new job.
The problem is not shown in the unemployment rate. It’s in the rate of people who have given up searching for jobs.
NVDA, INTC, AVGO and Oracle invested in ChatGPT #5. They can study Wolf’s Zillow charts on US and Canadian RE, Fed assets, Consumer spending, consumers debt, Manheim…and buy him out.
EFFF A.I. We are already dealing with it when we chat or call and a Automated Bot says, “I know you want an Agent, but please tell me if it is one of the following choices…” – – wasting time. Causing Irritation.
“Acemoglu’s advice: “Think about what it is that’s so special about your company and your workforce and think about amplifying that, rather than just automating it.”
This guy gets it.
Robosapiens will amplify better, faster, and cheaper than the hu-mans.
Fear the Fed and governments, not AI. That says it all. Thanks Mish!
Cryptocurrencies and AI are massive electricity hogs. We’ll see how John Q Public feels about AI gobbling up electricity if/when rates become unaffordable for actual human needs vs hypothetical technological advancement exceeding daily human requirements. Sorry folks, no affordable A/C (Phoenix), furnace fans (north), or hot water (everywhere) as we need to “mine” Bitcoin and produce thus-far negligible advancement AI products.
It’s a huge capital hog which will likely result in severe financial dislocations when those that do not produce profitable products from it go belly up. The winners will surely be VERY profitable. However, it cannot come at the expense of basic daily human needs.
Of course as long as John Q Public owns NVDIA they could afford to buy a lot more than the electricity in this bifurcated bubblish market.
The real Doomsday Machine is the human race
OR
Name one net benefit we have ever delivered to Planet Earth
well … if we assign a consciousness or personality to the planet, then I would say fulfilling the purpose of creating intelligent life. I don’t think that way but I’m playing your game. this is kind of like me asking you what benefit you produced for your mother’s womb.
Well, there’s you. And you’re pretty special, Rando. Don’t sell yourself short.
Does your existence make up for all those empty Pepsi cans you didn’t sort before tossing in the rubbish? I’m not sure. But I think you got a pretty good case!
Just how does AI differentiate between the real and the unreal? Disinformation will stymy AI just as fast as the actual thing.
It doesn’t. How could it? At best its connection with reality is getting its keyboard tickled or looking out of a crappy camera.
>> Just how does AI differentiate between the real and the unreal?
Cameras, microphones, smoke detectors, air monitors, spectrometers, Geiger counters, etc.
Think about humans believing tons of misinformation, especially all that nonsense from their governments. Are robosapiens less intelligent or capable or whatever than homosapiens for it?
No matter what the sensor is, all the AI gets is a stream of numbers.
How do you know that humans don’t also transcribe the inputs from our senses into digital format?
I remind you that after centuries of brain research, we STILL don’t understand how data is stored or retrieved in our brains. SAD!
However it’s stored, it’s damn unlikely to be digital. Meat doesn’t make reliable 1s and 0s.
While analog at its core, the higher-order logic supported by analog circuitry looks quite similar to that by digital circuitry. I suspect the analog-digital distinction yields little difference as the overall complexity increases.
What does this even mean?
As we can plainly see, EVERYTHING can be represented by a string of numbers. The key is how those numbers are interpreted.
Artwork, music, words on a page, books, photography, location, TV programs, etc. can all be represented as numbers.
And sure, there are those very special people who have very expensive high end audio systems where they claim that analog wax records sound “better” than digital CD’s/streams. Perhaps they do but it isn’t enough to matter to the vast majority.
You might also look at living things. Consider your hand, which feels a certain way. It has warmth. It is flexible. It can move under the direction of your brain. It can hurt if you bang it into or against something. And yet, it is just an assembly of inanimate atoms!
Disinformation stymies humans, including many here. What should be done about this?
“It’s tough to make predictions, especially about the future” …