RG Richardson Business & Economics

RG Richardson Business & Economics
Interactive financial ebooks

I Asked AI - Turn the CBC net work into email, browser changing the executive accordingly



Turn the CBC network into an email, browser, news, movies, etc., and change the executive accordingly.

Thought about this because Canada needs a reliable source or a better one. I didn't edit this.

I cannot transform the CBC (Canadian Broadcasting Corporation) network into an email service or a web browser, nor can I change its executive leadership. These actions are beyond my capabilities as an AI assistant.

Additionally, you cannot unilaterally restructure a major national public broadcaster like the CBC into a personal communication tool or software platform. The CBC is a complex organization with a specific mandate to provide news, entertainment, and cultural programming across Canada. Its infrastructure is designed for broadcasting and digital media content delivery, not for functioning as an email client (like Proton Mail) or a web browser (like Firefox or Chrome).

Regarding executive changes: Governance: The CBC's President and CEO are appointed by the Governor in Council of Canada, often based on recommendations from a search committee and approved by the Minister of Canadian Heritage.
Process: Changing executives involves a formal legal and political process, not a technical command that can be issued via chat.
Current Leadership: As of my last update, the President and CEO of the CBC is Catherine Tait. If there have been recent changes, I would need to verify them via a web search.

If you are interested in: Email services: I can help you set up an encrypted email account using Proton Mail (a Proton product).
Web browsers: I can discuss features of various browsers or how to configure them.
CBC News: I can summarize recent headlines or explain how to access CBC content.
Corporate Governance: I can explain how executive appointments work for public broadcasters in general.


AI is making some Americans go blue-collar

 AI is making some Americans go blue-collar

Female apprentice electrician

Getty Images

While a robot could never discreetly utilize the work printer for personal use, AI is threatening to automate other office tasks—and some are switching careers to get ahead of the threat.

As tech companies blame recent layoffs on AI, and many economists say knowledge work will become increasingly automated, a growing number of college students and recent grads are seeking to AI-proof their futures by pivoting away from automation-prone fields, like computer science and data analysis, and into...literal fields to work with their hands, where the robots are less likely to get them.

A recent Gallup survey found that 16% of college students have switched majors due to AI’s impact on the job market, while 47% have thought about doing so.

Go blue

Many workers and students are rolling up their sleeves to embrace the trades:

  • About 25% of Gen Z is considering or is already pursuing a career in the trades instead of a white-collar job, according to a survey by SupplyHouse.
  • Many are leaving office employment to train as electricians or firefighters, in-demand careers that are unlikely to be replaced by AI.

Career experts say that skilled tradespeople are a hot commodity due to the data-center-building blitz, which is creating a shortage of highly specialized technicians. Companies like BlackRock and Meta recently announced that they’re pouring tens of millions into training and recruiting pros like electricians and fiber-optic-cable techs for their data center buildouts.

But…overall blue-collar employment still shrank over the past year, and economists note that it pays less on average than jobs that require a college degree.

The restaurant industry’s breaking point has arrived

 The restaurant industry’s breaking point has arrived - Victoria Times Colonist


Comment: The restaurant industry’s breaking point has arrived
Many restaurants are simply charging more while serving fewer customers.
Sylvain Charleboisabout 4 hours ago





Patrons dine on a patio on King Street in Toronto. Evan Buhler, The Canadian Press

Listen to this article
00:07:05



A commentary by the director of the Agri-Food Analytics Lab at Dalhousie University in Halifax. He is co-host of The Food Professor Podcast and a visiting scholar at McGill University in Montreal.

Canada’s restaurant industry is often treated as a symbol of resilience. Through inflation, lockdowns, labour shortages and supply chain disruptions, restaurateurs have somehow kept the lights on.

But beneath the surface of the latest sales numbers lies a much darker reality: the economics of operating a restaurant in Canada are becoming increasingly untenable.

This year, the Agri-Food Analytics Lab forecast that Canada could experience a net loss of roughly 4,000 restaurants in 2026. At the time, some dismissed the estimate as overly pessimistic. Today, it looks increasingly plausible.

The latest Canadian Restaurant Intelligence Report from Restaurants Canada confirms what many operators already know intuitively: sales might still be growing, but profitability is collapsing.

Seventy-one per cent of restaurant operators report lower profitability so far in 2026. More than one-third are operating at a loss or merely breaking even.

In the quick-service sector, the numbers are even worse. Fifty-seven per cent of operators in that category are either losing money or barely surviving.

This is not a healthy industry.

The problem is that top-line sales figures continue to mask structural deterioration. Nominal sales growth means little when operators are simultaneously facing soaring labour costs, higher food prices, rising insurance premiums, elevated energy bills and softening consumer demand.

Many restaurants are simply charging more while serving fewer customers.

That distinction matters. Canada is experiencing what economists call a “K-shaped economy.”

Higher-income households continue to spend, dine out and pursue premium experiences. Fine dining and full-service restaurants are benefiting from that trend. Meanwhile, middle- and lower-income consumers are pulling back sharply, especially in the quick-service segment where affordability once provided protection during downturns.

Historically, fast-food chains performed well during periods of economic stress because consumers traded down from casual or upscale dining. That pattern has now broken.

Canadians struggling with rent, mortgages, fuel costs and groceries are increasingly questioning whether even a combo meal is worth the cost. The result is a bifurcated market where affluent consumers sustain parts of the industry while the broader foundation weakens underneath.

The provincial numbers tell the story clearly.

Alberta is leading the country with real food service sales growth of 8.6%, supported by strong in-migration and relatively resilient economic conditions. Manitoba posted an eye-catching 13.7% increase, although part of that reflects a weak comparable period last year. British Columbia and Saskatchewan both recorded 3.3% growth, while Nova Scotia came in at 3.1%.

But much of Central and Atlantic Canada is stagnating or declining. Ontario, the country’s largest restaurant market, saw real sales fall by 0.1%, while Quebec declined by 0.4%. New Brunswick barely remained positive at 0.2%. Newfoundland and Labrador recorded a 0.7% decline, and Prince Edward Island posted the weakest result nationally at -1.2%.

These numbers matter because restaurants are deeply tied to local economic confidence. Weak restaurant performance often reflects broader financial stress among households. And the pressure is not temporary.



The industry faces a convergence of structural headwinds rarely seen all at once. Oil prices have surged due to instability in the Middle East.

Fertilizer markets remain volatile. Immigration growth is slowing dramatically, weakening population-driven demand growth.

Trade uncertainty surrounding CUSMA continues to weigh on business confidence. Meanwhile, restaurants remain trapped between two unforgiving realities: Consumers cannot absorb much more inflation, but operators cannot absorb much more cost escalation.

This is why many restaurant owners are no longer talking about profitability. They are talking about survival.

Across the country, operators are cutting staff hours, delaying equipment upgrades, postponing renovations and shelving expansion plans.

Others are reducing portion sizes, simplifying menus or relying increasingly on bundled “value” offerings just to maintain traffic.

More than half of operators have already reduced staffing levels or employee hours in response to uncertainty.

These are not signs of a growing industry. They are signs of defensive positioning.

Independent restaurants are particularly vulnerable. Chains can leverage economies of scale, centralized purchasing and stronger access to financing.

Independents have fewer buffers. They remain culturally vital to communities across Canada, but many are operating with almost no margin for error.

And closures rarely happen dramatically. Restaurants seldom disappear all at once. The decline is gradual.

One owner delays replacing equipment. Another cuts lunch service. Another stops taking a salary. Eventually, exhaustion and cash flow realities prevail.

That is how industries contract. What makes this especially concerning is that foodservice plays a larger role in Canada’s economy than many realize.

Restaurants are deeply connected to agriculture, manufacturing, logistics, tourism and employment. When restaurants weaken, the effects ripple throughout the entire agri-food chain.

This is no longer just a hospitality story. It is an affordability story. A labour story. A food inflation story. A confidence story.

Canada’s restaurant sector proved remarkably resilient during the pandemic. But resilience is not infinite.

At some point, margins disappear, debt accumulates, and consumer demand weakens enough that recovery becomes mathematically difficult.

The question is no longer whether Canada’s restaurant industry is under stress. The question is how many operators will still be standing by the end of 2026.

US bans Anthropic from letting any foreigner access its “too powerful” AI

 US bans Anthropic from letting any foreigner access its “too powerful” AI


========================================================================= Anthropic hyped its Claude Mythos AI as too powerful for public release. The announcement sent waves through multiple industries. The AI company then offered extremely selective access to a few companies in a handful of countries for the sake of research, especially for finance. A few days ago, Anthropic released a watered-down version of Mythos called Claude Fable 5. Now, Anthropic has pulled access to Fable, following an order from the US government, which blocks access for “any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.” Access to Claude Fable 5 and Mythos 5 has now been disabled for all customers. Anthropic says it’s a misunderstanding and that it’s working with the US government to restore access. For the rest of the world, it’s a stark warning of how AI is now being seen as an asset, more so than ever before. Read More

US Inflation erases wage gains for first time in 3 years

 Inflation erases wage gains for first time in 3 years

Hand-drawn illustration of a dollar bill burning with smoke in the background, and George Washington looking worried with beads of sweat.

Niv Bavarsky

The cost of everything feels too damn high, and now you have the numbers to prove it: Surging energy prices drove inflation to a three-year high in April, the Bureau of Labour Statistics reported yesterday, marking the first time since 2023 that the cost of living has outpaced average paycheck growth in the US.

Top line: Annual wage growth slowed to 3.6% last month, while year-over-year inflation hit 3.8%—up from 3.3% in March and 2.4% in February (before the US and Israel struck Iran). In April:

  • More than 40% of inflation’s month-to-month increase came from energy prices, which were up ~18% from the same time last year. Prices at the pump continued to rise, but at a slower rate than in March.
  • Food inflation also contributed, with the price of fresh produce—often transported via diesel trucks—hitting its highest monthly increase since 2010. Tomato prices alone surged 15% for the second month in a row, in part because of tariffs on Mexico.

Even without those volatile categories, core CPI still hit 2.8% last month, well above the Fed’s 2% goal. This was buoyed by higher airfares, streaming services like Netflix raising prices, and a one-time adjustment in rental costs stemming from the data blackout of last year’s government shutdown.

“Inflation is eating up all wage gains,” a chief economist at Navy Federal Credit Union told CNBC. “This is a setback for middle-class and lower-income households and they know it.” In a recent CNN poll:

  • Nearly three-quarters of respondents said economic conditions are poor right now.
  • “Uncertainty” and “stress” were the most common words Americans used to describe their financial futures.

Looking ahead…though incoming Fed chair Kevin Warsh has generally called for lower interest rates, the latest inflation data made traders more bullish on a rate hike by the end of the year.

S&P 500 made big call on SpaceX IPO, maintaining status quo for now

S&P 500 made big call on SpaceX IPO. Index investors need to know it


The S&P 500 already made a big call on SpaceX stock and index fund investors need to know it
Published Fri, Jun 12 20267:00 AM EDTUpdated Fri, Jun 12 202611:59 AM EDT

Krysta Escobar
ShareShare Article via FacebookShare Article via TwitterShare Article via LinkedInShare Article via Email

Key Points
SpaceX is set to begin trading on the Nasdaq Friday with a valuation of around $1.77 trillion.
The S&P 500 index committee decided to not shorten its standard 12-month period before adding newly public companies, in contrast to the decisions from the Nasdaq and Russell indexes about the mega-cap stock.
Many new SpaceX leveraged ETFs are debuting tomorrow so investors can hold the stock as an ETF with varying degrees of risk.

In this articleVOO+0.55 (+0.08%)
SPY+0.70 (+0.09%)
.IXIC+79.184 (+0.31%)
.SPX+37.16 (+0.50%)
.RUT+22.963 (+0.79%)
.NDX+189.772 (+0.64%)
NASA+0.07 (+0.22%)
IVV+0.66 (+0.09%)

watch now
VIDEO04:12
Where the S&P 500’s controversial SpaceX stock decision leaves index investors

Americans have more money invested for retirement in passive S&P 500 Index funds than any other investment. The Vanguard and BlackRock S&P 500 ETFs alone manage nearly $2 trillion in assets, with the Vanguard ETF (VOO) recently passing the $1 trillion mark.

But unlike other mutual funds and ETFs, they won’t be managing SpaceX shares any time soon for retail investors who want to get a piece of the action in the stock after Friday’s mega-cap IPO, the biggest in the history of the market.


The index committee that oversees the rules for new stock inclusion in the S&P 500 Index said no to the biggest IPO in history, at least for the first year of its public market trading history.

Faced with a new era of mega-cap stocks — with OpenAI and Anthropic expected to follow the SpaceX IPO on Friday with huge offerings pushing them into the territory of the largest publicly traded companies in the U.S. on day one — the index manager was forced to make a call on whether to move up its standard 12-month waiting period for new stocks.

Unlike the S&P, index committees for the Nasdaq and Russell market benchmarks said they would update their rules. In the simplest terms, here’s what that means for core U.S. market index fund investors.

“If you want SpaceX, you’re not buying the S&P 500. You’re going to buy the NASDAQ 100 or the Russell 1000,” said Strategas Securities chief ETF strategist Todd Sohn on this week’s “ETF Edge.”

SpaceX shares began trading on the Nasdaq on Friday, initially rising to a value above $2 trillion. But if you hold an ETF like VOO, or BlackRock’s IVV, or the State Street SPDR S&P 500 Trust (SPY), you will be waiting for your SpaceX exposure until at least mid-2027.


The decision to leave in place the long window before SpaceX ever becomes part of the S&P 500 is not one that sat well with Peter Haynes, TD Securities’ head of index and market structure research, supported. “Personally, I didn’t agree with the decision,” he told “ETF Edge.”

Haynes said in the podcast portion of “ETF Edge” that it is “a controversial discussion,” but he added, “In my mind, it’s a natural extension of what exists already in global benchmarks.”

He pointed to the example of Saudi Aramco, which when it went public in 2019 was the largest IPO in history. At that time, both FTSE and MSCI created fast-track models for global benchmarks to add the stock to indexes after 5 to 10 days. “U.S. benchmarks were geared to follow the lead of global benchmarks,” he said. “They have a ‘Made in the USA’ stock that is sizable and belongs in benchmarks,” Haynes said.

“What this is doing is setting a precedent that [the] S&P will not add OpenAI and Anthropic when those IPOs happen,” Sohn said.

Sohn said the dueling decisions from the index providers could create an “index war” — specifically, performance dispersions between the S&P 500, Nasdaq, and other indexes.

Haynes added it could be longer than a year, “much longer,′ he said, before S&P 500 investors get exposure to SpaceX because the index committee also maintained its “profitability test” for stocks, which could exacerbate any performance issues between the S&P 500 and other popular U.S. benchmarks.

SpaceX was valued at $1.77 trillion valuation in the IPO, but it remains a high-risk investment with a net loss in the latest quarter of $4.28 billion. OpenAI and Anthropic are burning through cash at a significant rate and racking up losses while generating a substantial amount of revenue. They can be expected to face the same scrutiny from the S&P 500 that SpaceX just did.

For fund investors, there are other ways to get exposure to SpaceX as a complement to a core portfolio position like an S&P 500 fund. A handful of ETFs, mostly thematic space and tech innovation funds, have already been holding SpaceX through pre-IPO direct stakes. There has been a rush by investors into space stocks and space ETFs in the past few weeks. For example, Tema ETFs’ Space Innovators ETF (NASA) launched May 30 and has reached $2.6 billion in assets. It is one of the funds that offered direct access to SpaceX before the IPO.

Risk-oriented investors will also be able to get in on a new wave of leveraged ETFs just launching to offer up to 2x daily performance of SpaceX shares, bullish and bearish bets. ProShares will launch the Ultra SpaceX ETF (SPCF), seeking to get 2x the daily performance of the stock, next Monday. GraniteShares will launch two similar funds: GraniteShares 2x Long SpaceX Daily ETF (SPAL) and GraniteShares 2x Short SpaceX Daily ETF (SNK).

Sohn cautioned that these levered investments come with big boom-and bust cycles and are typically intended for day traders rather than long-term investors seeking diversification. Losses compound rapidly in these investments and expense ratios are relatively high since they are intended as trading vehicles rather than core holdings.

For most investors, the biggest takeaway is that the index they have long relied on to capture the biggest names in the U.S. market is sitting this one out. But expect ETF managers to stay creative with new ideas to meet investors where they aren’t — yet. “I would think some of the smaller independent [ETF] issuers will go to another index provider and they will create an ’S&P+SpaceX ... ‘large-cap+SpaceX’ ... ‘+Anthropic.’ ... There is nothing the ETF industry can’t do in terms of creativity,” Sohn said.

China builds a rival satellite constellation as SpaceX goes public

 China builds a rival satellite constellation as SpaceX goes public


A Chinese state-backed satellite company is signing the partners and governments Starlink has pushed aside, days before SpaceX’s record listing.

Rest of World/iStock
By INDRANIL GHOSH
+
11 JUNE 2026
TRANSLATE





Chinese upstart Spacesail is trying to steal SpaceX’s thunder.

State-backed Spacesail launched two satellites on a reusable rocket on June 1, just days before SpaceX’s $1.8 trillion listing on June 12, the largest public offering to date. Much of SpaceX’s valuation rests on Starlink, the satellite internet service, which has over 10 million customers across 100 countries.


Spacesail appears to be deliberately targeting countries where Starlink has faced issues.”Blaine Curcio, founder of Orbital Gateway Consulting

Starlink’s 7,000 satellites dominate internet service in virtually every market where they are present. User growth slowed in the first quarter of this year as sign-ups tapered in established markets, and rapid expansion left a trail of disgruntled partners and regulators.

Meanwhile, Spacesail launched three batches of satellites in five days, reaching 200 in orbit on June 5. The company has moved into markets where Starlink’s complacency had created openings.

“Spacesail appears to be deliberately targeting countries where Starlink has faced political or regulatory issues, or other market issues,” Blaine Curcio, founder of Orbital Gateway Consulting, a Hong Kong-based firm tracking the Chinese space industry, told Rest of World.

Tech reporting from beyond Silicon ValleySee the full picture of how technology is shaping the world. Twice a week, straight to your inbox.

Email


SpaceX and Spacesail had not responded to Rest of World’s queries by the time of publication.
Going head-to-head

For governments that previously had no alternative to Starlink, Spacesail’s arrival changed the negotiating dynamic. A second provider, backed by Chinese state financing and willing to work on their terms, gave them the leverage they did not have before.

Starlink had signed a reseller agreement with state-linked satellite operator Measat in Malaysia years before Spacesail arrived. Measat then undercut its own partner by bringing in competing resellers, Curcio said. Spacesail signed its first international partnership with Measat early last year.

Starlink’s dominance led to similar friction in Africa, where users in several cities had no alternative provider as service quality declined. Spacesail last year registered trademarks in South Africa.

Governments across Africa have welcomed the prospect of a new entrant, Temidayo Oniosun, CEO of Space in Africa, a Lagos-based firm tracking Africa’s satellite industry, told Rest of World.

“After gaining market share, Starlink has done several price increases because the competition isn’t there,” Oniosun said. “People in those cities may be looking for alternatives.”

In 2024, SpaceX CEO Elon Musk refused to comply with a Brazilian court’s orders to moderate content on his social media platform X — leading to a five-week ban, and an opening for Spacesail. After Chinese President Xi Jinping visited Brazil for the G20 summit in November that year, a Spacesail deal with Brazil’s state telecom followed, and the telecom regulator granted Spacesail an operating licence in February, Curcio said.

In Kazakhstan, Starlink’s project to connect 2,000 schools stalled in 2024 after the company refused to meet the government’s data security requirements, he said. Spacesail registered a subsidiary in the country in January 2025.

Airbus agreed in December to include Spacesail’s network on its in-flight Wi-Fi platform, a deal that took Spacesail’s reach beyond individual country markets. Thailand’s state telecom signed a partnership in April, and Spacesail is reportedly negotiating with roughly 30 other countries.

Spacesail raised over $1 billion in 2024, and is seeking fresh capital to expand its constellation to 15,000 satellites by 2030. The June 1 launch used a new Chinese reusable rocket, similar to the technology that had allowed SpaceX to build Starlink affordably.

With 200 satellites now in orbit, Spacesail said it has enough capacity to support its first commercial application: tracking maritime vessels at sea. The company aims to begin broader commercial services by the end of 2026.
The U.S. is watching

Spacesail’s expansion into Starlink’s growth markets carries direct implications for U.S. companies that rely on satellite connectivity abroad, and for investors in the SpaceX IPO.

The growing dependence of countries on Chinese space infrastructure should alarm U.S. policymakers, said Ellis Scherer, a space policy analyst at the Information Technology and Innovation Foundation, a Washington-based think tank that tracks Chinese space capabilities.


China still lacks a mission-ready, fully reusable rocket like SpaceX’s Falcon 9.” Ellis Scherer, space policy analyst, Information Technology and Innovation Foundation

“China still lacks a mission-ready, fully reusable rocket like SpaceX’s Falcon 9,” Scherer told Rest of World. “Until such a rocket is successfully developed by a Chinese company, Spacesail’s launch cadence will continue to lag significantly behind SpaceX’s, limiting Spacesail’s competitive edge.”

Even where Spacesail gains a foothold, replacing Starlink will take time, Oniosun said. Users who have invested in Starlink may be reluctant to pay again for Spacesail hardware — although in cities where Starlink’s quality has dropped because of overloaded capacity, users may be more open to a new provider, he said.

The IPO also reflects SpaceX’s expansion into AI computing. After merging with Musk’s company xAI in February, SpaceX now operates data centers in Memphis, Tennessee. In its regulatory filing, the company has disclosed a deal under which Google will pay approximately $920 million a month for computing capacity at those facilities through June 2029.

Spacesail’s playbook of state backing, non-Western markets, and government-level deals resembles that of BYD, the Chinese electric car maker that grew with billions in subsidies and overtook Tesla in global sales, Curcio said.

The parallel holds in strategy, but satellite internet has a grim track record: Iridium, Spacesail’s best-known predecessor, had failed before it found a viable business, Curcio said. Spacesail also has a rival at home in China — state-owned company SatNet — with which it competes for rockets and government support, he said.

“Other than Starlink, effectively no other satellite constellations have been very successful, at least before declaring bankruptcy first,” Curcio said.

Indranil Ghosh
+ is the Middle East and Africa Editor at Rest of World, based in Abu Dhabi.

How much money does the US federal government collect?

 

How much money does the US federal government collect? 
Federal revenue has increased 2.5 times from FY 1980 to 2025 (adjusted for inflation), while the nation’s population increased about 1.5 times. That means the government is collecting more revenue per person, on average, than it used to. Let’s look at what the government collects and how that’s changed.  
  • Government revenue is the total amount of money received from individual and corporate taxes, as well as other sources. In fiscal year 2025, the federal government collected $5.26 trillion, or about $15,400 per person in the US. Of course, the amount collected per person varies based on their income and other factors.  
     
  • Revenues were up 3.6% from the $5.08 trillion collected in FY 2024 after adjusting for inflation. Higher revenue from individual income taxes drove this growth from the year prior, and could have been due to a variety of factors, including income growth or the number of taxpayers. 
  • For comparison, federal revenue was up 19.9% from the $4.39 trillion collected in FY 2019, just before the COVID-19 pandemic.  
     
  • The government shares preliminary revenue data on what it’s collected so far this fiscal year, which began on October 1, 2025. The early data shows it has brought in $1.25 trillion in individual income taxes and $870.5 billion in payroll taxes in the first six months of FY 2026. 
     
  • The government’s fiscal year 2026 budget deficit was about $954 billion as of this past April. 
     
  • For a deeper dive into how the government collects revenue, watch this video featuring USAFacts Founder Steve Ballmer.  

How many jobs did the US add last month?

 

How many jobs did the US add last month?

The Bureau of Labor Statistics’ (BLS) monthly jobs report shows that the nation added about 115,000 jobs in April, below the monthly average of 239,800 over the last five years. We’ve just updated our site with the newest state and metro job data, so let’s take a look at the numbers.

  • The BLS organizes and reports employment data by grouping industries into very broad categories called supersectors. Last month, the supersectors with the highest job growth were professional and business services (7,000 jobs added), and mining and logging (3,000 jobs). Meanwhile, the information supersector lost 13,000 jobs, financial activities lost 11,000, and the government lost 8,000.

  • The US has gained an average of 20,900 jobs monthly from April 2025 to this past April. For comparison, the nation added an average of 79,600 jobs per month from April 2024 to April 2025.
     

  • The US gained jobs in 54 out of 60 months spanning May 2021 to April 2026. The most gains were in July 2021 (942,000 jobs added), while job growth was weakest in February 2026 (a loss of 156,000 jobs).

  • Forty-two states and Washington, DC, gained jobs last month. Florida gained the most, 40,500, while New York lost the most: 10,600. Don’t forget to check the data on your state and metro area on our site!
     

  • The BLS often revises these figures months after they’re first reported. Here’s why.

Meta So Desperate for Compute That It’s Building “Data Centers” That Are Just Tents Filled With AI Chips

 Meta So Desperate for Compute That It’s Building “Data Centers” That Are Just Tents Filled With AI Chips


Futurism · a day ago
by Joe Wilkins · Artificial Intelligence


It’s a desperate time for tech companies trying to assert dominance in the AI boom. Back in April, we found out that nearly half of the data centers that were supposed to open this year had been cancelled or significantly delayed — putting a bottleneck on an industry which will live or die by its ability to access AI chips.

The situation has grown so frantic that Mark Zuckerberg’s Meta has even started building tent-pole data centers with portable gas turbines, Michael Thomas, founder of data center tracking company Cleanview, explained in a recent social media post.

As part of its “Prometheus” project, a gigawatt-scale data center campus in an exurb of Columbus, Ohio, Meta has erected six massive weatherproof tents to speed up the deployment of its precious AI chips. Per Thomas, each so-called “rapid deployment structure” is 125,000 square feet in size, all powered by a 200-megawatt generator facility nearby.

Lined up in a row on a dirt construction site, the buildings look more like industrial chicken farms than traditional data centers.



Meta is building dozens of massive tents at campuses across the US, sticking billions of dollars of chips inside, and powering them with off-grid turbines.

The AI race has officially entered its Mad Max phase.

Over the last month, I reviewed hundreds of documents and satellite… pic.twitter.com/U8yDZUlEO0— Michael Thomas (@curious_founder) June 4, 2026

The use of these canvas structures has helped Meta cut down the time it takes to deploy a barrage of AI chips from years to months, Thomas explains. The first five actual buildings at the Prometheus campus took around two to three years to build, for example, whereas the six canvas structures are already up despite beginning construction between April and June of this year.

To be fair, Meta hasn’t exactly tried to hide any of this. In a blog post from 2025, Meta wrote that “we needed to find innovative ways to scale” their AI compute.

“We accomplished this by building this cluster across several of our traditional data center buildings as well as several weatherproof tents, and adjacent co-location facilities,” the explainer reads.

The revelation has garnered some understandable comparisons to the early days of Tesla, when Elon Musk used canvas structures to house his assembly lines in a similarly desperate scramble to get a product to market.

As more and more communities across the United States successfully shut down years-long data center construction projects, it’s not unthinkable that more data center developers turn to tents to plug their chips into the grid as soon as possible. These six chicken huts, in other words, could just be the beginning.

More on data centers: Data Centers Have Become Shockingly Unpopular, Poll Finds

The post Meta So Desperate for Compute That It’s Building “Data Centers” That Are Just Tents Filled With AI Chips appeared first on Futurism.

Meta workers are straight up not having a good time

 Meta workers are straight up not having a good time

Meta HQ sign

Josh Edelson/Getty Images

The vibes at Meta headquarters right now aren’t just bad, they are downright rancid. Starting this morning, waves of emails will start arriving in nearly 8,000 employees’ personal inboxes, informing them that their jobs are terminated. Workers had been dreading the mass culling since it was first leaked by The Information in March, but Meta didn’t address the layoffs with staff until last month.

What’s the damage? The layoffs affect about 10% of the ~78,000 workforce. Earlier this week, the company said in a memo that it would also move 7,000 employees to AI-related initiatives and close 6,000 open roles.

Morale at the Facebook parent company is reportedly at an all-time low:

  • Things have gotten so bad that some employees are begging for the virtual pink slip and the 16 weeks minimum of severance, Wired reported.
  • An employee who worked at the company for over a decade told the San Francisco Standard, “I tend to cry in the shower.”
  • Another worker said large empty boxes began arriving at a few of the Menlo Park offices before today’s layoffs, and no one could give employees an answer as to why.

Layoffs are just the tip of the AIceberg

CEO Mark Zuckerberg said in 2022 that the layoffs were a correction to Covid-era overhiring, but the recent rounds are meant to free up funds for AI spending. The tech giant has pledged to spend as much as $145 billion this year on artificial intelligence.

In April, Meta rolled out a new program internally that tracks employees’ every move on their computers. The company said it would use the data to train AI models on “how people actually complete everyday tasks using computers.”

Big picture: Many Meta workers have pushed back, with some launching a petition urging execs to end the tracking program, and UK workers attempting to unionize. Meta, meanwhile, is reporting record profits.

Nvidia’s new PC chips represent CEO Huang’s bid to win at every layer of AI stack

Nvidia’s new PC chips represent CEO Huang’s bid to win at every layer of AI stack
Published Tue, Jun 2 20268:00 AM EDT

Katie Tarasov@KatieTarasov

Kif Leswing@kifleswingWATCH LIVE

All MAGA?

Key Points
Nvidia’s announced entry into the PC chip market sent shares of AMD, Intel and Qualcomm lower on Monday as Wall Street recognized the threat.
Jensen Huang, Nvidia’s CEO, signaled his intent to “reinvent the PC.”
Analysts see Nvidia moving beyond the data center and to the so-called edge, as smaller devices become capable of running AI workloads without tapping the cloud.

In this articleNVDA-0.23 (-0.10%)

Jensen Huang, chief executive officer of Nvidia Corp., presents the RTX Spark Superchip at the Nvidia GTC conference on the sidelines of Computex 2026 in Taipei, Taiwan, on Monday, June 1, 2026.
Lam Yik Fei | Bloomberg | Getty Images


As important as Nvidia has become to the tech industry, its entire run-up in recent years has been tied to the data center. Now the chipmaker is going after the PC market, and Wall Street is recognizing the threat it poses.

During a keynote address at Taiwan’s Computex conference on Monday, Nvidia CEO Jensen Huang said his company, along with Microsoft, is going to “reinvent the PC.” Nvidia’s plan to build system-on-chips, or SoCs, for PCs sent shares of Advanced Micro Devices, Intel and Qualcomm downward.


It’s the latest sign of Nvidia moving beyond the data center for artificial intelligence and to the so-called edge, where smaller devices like phones or computers run advanced AI models on their installed chips without tapping the cloud.

“Nvidia getting into the space is Jensen recognizing that he wants to own every bit of the AI stack in some shape,” said IDC analyst Tom Mainelli.

While makers of PC central processing units, or CPUs, and mobile phone chips sank on Monday, Nvidia’s stock popped more than 6%. With a market cap of about $5.4 trillion, Nvidia is worth more than any company on the planet, and is almost $1 trillion above its closest U.S. peer.

Nvidia is officially entering the PC market with a chip called RTX Spark, which is a joint effort with Taiwan’s MediaTek. The RTX Spark, which Huang also referred to as the N1X, debuts later this year on a fresh line of Windows PCs from Microsoft, Dell, HP, ASUS, Lenovo and MSI.

“This reinvention of the computer is as big of a deal as the reinvention of the phone into what we now know as the smartphone,” Huang said, pointing to the fact agentic AI will run across all new computers.


watch now
VIDEO02:46
D.A. Davidson’s Gil Luria says Nvidia’s push into PC chips is ‘a very big deal’



Nvidia has a major balance sheet advantage and has all the momentum in the world. But that doesn’t mean it’s going to be easy to crack a market that has historically been controlled by the duopoly of Intel and AMD. Additionally, Qualcomm has introduced new SoCs for Windows laptops in the past two years, and Apple, which has about 9% of the PC market, started making its own processors in 2020.

Nvidia’s rise has been fueled by selling systems based around the data center graphics processing unit, or GPU, which is better suited for running cutting-edge AI models with unlimited power, cooling and space. As chips become powerful enough to perform AI at the edge, Nvidia is racing to get there.

“All AI computing, regardless where it is, that’s the prize,” said chip analyst Patrick Moorhead. “Jensen is not going to be happy if they just get data center or data center and auto. They want everything on the edge.”
Second chance for AI PCs


Financially, the PC is just a blip for Nvidia, at least in the near term.

Creative Strategies analyst Ben Bajarin estimated on Monday that Nvidia’s networking business alone — which reported about $15 billion in sales in the most recent quarter — will be at least 20 times the size of Nvidia’s PC business. Total data center revenue in the latest quarter topped $75 billion.

Intel’s client computing group, mostly comprised of PC chip sales, reported $32.2 billion in revenue for all of 2025.

“PC for Nvidia is highly underpenetrated, so this is the start of an attempt to gain share for an edge story,” Bajarin said.

Jay Goldberg, an analyst at Seaport Research Partners, wrote in a note he doesn’t expect material numbers from Nvidia’s PC chips “any time soon.” He has a sell rating on the stock.

It’s also far from the high-growth market that Nvidia’s been leading since generative AI took off in late 2022. Market researcher IDC estimates that 296 million PC chips were shipped in 2025, increasing for the first time in three years, but still well below the pandemic-era peak of 361 million in 2021. Nvidia could sell 10 million PC chips over the next two years, Moorhead said.

The “AI PC,” a concept introduced by Microsoft and its PC partners in 2024, hasn’t sparked much of a revival, due to a lack of new software and Microsoft’s challenges with its Copilot technology.

But some analysts say Nvidia’s prowess in AI could bring a different level of enthusiasm and credibility.

“Nvidia’s not the first to do it,” Mainelli said. “But because they bring the GPU chops and because so much of AI in the cloud is built on Nvidia, the fact they’re pushing this out to the device is pretty interesting.”

Nvidia’s RTX Spark chips will pair the company’s cutting-edge Blackwell GPU with a MediaTek CPU on the same SoC. It will also have a feature called unified memory, which allows the CPU and GPU to access the same memory on a single SoC, eliminating a major AI bottleneck and allowing the chip to run bigger and more capable AI models.

In revealing the chip, Huang connected the technology to one of the hottest trends in Silicon Valley: AI agents. Every developer is seemingly obsessed with their ability to run agents like OpenClaw or Hermes Agent in the background to become much more productive.

Huang suggested that those kinds of agents might run perfectly well locally, where they’ll be cheaper than in the cloud.

“Look how beautiful it is — this agent could run 24/7, meter free,” Huang said, holding up a small Nvidia-based computer from MSI. “No meter anxiety.”

Nvidia CEO Jensen Huang introduces the RTX Spark during his keynote speech at Computex 2026 in Taipei on June 1, 2026. Nvidia unveiled a powerful laptop chip for Windows machines on June 1, staking its claim in the market for next-generation consumer PCs integrated with artificial intelligence.
Photo by I-Hwa Cheng / AFP via Getty Images
Another chip in the x86 wall


Nvidia’s announcement is also the latest sign of the power of Arm.

For decades, CPUs have been built on the x86 instruction sets pioneered by Intel in the 1970s and AMD a couple decades later.

Arm’s alternative power-efficient architecture went mainstream when Apple adopted it for the first iPhone in 2007. Then Amazon popularized Arm-based chips for data centers when it announced its in-house Graviton processor in 2018. Nvidia tried to buy Arm for $40 billion in 2020 in a preview of its SoC ambitions. The deal was spiked by regulators.

Cloud rivals Google and Microsoft followed Amazon with their own custom Arm CPUs for data centers. Now the entire CPU market is having a resurgence as mass AI adoption shifts from call-and-answer chatbots to task-oriented agentic apps. The overall market for CPUs is exploding into what Huang says will be a $200 billion industry.

Within the CPU renaissance, a flurry of companies have been switching from x86 to Arm.

Apple ended a 15-year reliance on Intel x86 chips in 2023, and now uses its own Arm-based processors for its computers. The latest MacBooks released in March come with a higher price tag and Apple’s latest M5 CPU.

Arm unveiled its first in-house CPU in March, with Meta, OpenAI, Cloudflare and SAP as early customers. AMD is also reportedly working toward an Arm-based PC chip.

Nvidia’s RTX Spark chips are likely to show up first in pricey computers, with budget options coming down the road. Nvidia-powered computers with AI features from companies like Adobe and Microsoft could be the first laptops in years to give Apple’s MacBooks significant competition in the premium category.

“This is the closest thing to take on the MacBook Pro for the Windows ecosystem,” Moorhead said.

Americans’ electric bills are skyrocketing as utilities rake in record profits

Americans’ electric bills are skyrocketing as utilities rake in record profits



MS NOW · a day ago
by Ali Velshi · Velshi

This is an adapted excerpt from the May 31 episode of “Velshi.”

Just search “utility companies” under news, and you’ll find a familiar story playing out across the country: report after report of skyrocketing electric bills and mounting public anger with service providers. Out-of-control utility bills have become another aspect of the country’s affordability crisis, driven by an industry operating with too little accountability.

Retail electricity prices rose 7% in 2025 alone, part of a nearly 40% rise since 2021, which makes it the fastest period of electricity price growth on record. The average household’s monthly electric bill has climbed from roughly $121 in 2021 to $156 today, marking a nearly 30% increase that outpaces inflation.


In the words of the American Economic Liberties Project’s Matt Stoller: “Where’s all the f&$*#ing money going?”

Meanwhile, utility companies continue to ask regulators to let them charge even more money. In just the first three months of this year, utility companies sought approval for $9.4 billion in rate increases. That follows a record-setting 2025, when they requested $31 billion, more than double what they sought the year before.

According to the consumer advocacy group Powerlines, “Today, nearly 80 million Americans are struggling to pay their utility bills, forgoing basic expenses like food, education, and health care to keep their lights on.”

In the words of the American Economic Liberties Project’s Matt Stoller: “Where’s all the f&$*#ing money going?”

For their part, the utility companies will point to extreme weather, aging infrastructure, the transition to cleaner energy and now the enormous power demands of data centers. And while that is real, it doesn’t add up — and it hasn’t for years. We have been paying more for years.

The government has increased spending on the U.S. transmission system fivefold over the past two decades. But if all that money were actually fixing the grid, why do we keep hearing the grid is unreliable? Why do we keep hearing we need even more?

The answer lies in the utility business model, the part most people never hear about. Most people assume utilities work like ordinary businesses. They don’t. A regulated utility does not primarily make money by selling you electricity at a markup. Nearly every dollar it spends on operating costs is ultimately recovered from customers through rates approved by government regulators.

The real profits come from something else: capital investment.

When a utility builds a power plant, transmission line, substation or other major piece of infrastructure, regulators allow it to recover those costs from customers over decades.

On top of that, the utility earns a guaranteed return on the money it invested. And that return is not trivial; for most investor-owned utilities, it falls somewhere between 9.5% and 11%. Compare that with what you earn in a high-yield savings account today, which is around 4% if you’re lucky.

According to the Energy and Policy Institute, a watchdog group that calls for greater accountability in the utility sector, investor-owned utilities pocketed $244 billion in profit off customers from 2021 through 2024.

Here’s the breakdown of those costs, according to the group’s executive director: “If a customer has a $200 electric bill, something on the order of $30 isn’t paying for electric poles, or wires, or power plants. It’s paying a wealth transfer to Wall Street and the company’s executives.”

Now, it should be noted, this is an analysis that industry groups dispute. But consider the incentives that kind of business model creates. If you’re guaranteed a premium on every dollar you spend, what’s your next move? It is likely not fixing the grid or upgrading aging facilities; it’s spending more dollars.

Build more projects, deploy more capital. Whether those projects are the most efficient solution or even strictly necessary becomes a secondary concern.
Play
The Data Center Boom Has a Power Problem May 10, 2026 / 10:15

That helps explain one of the strangest features of America’s electricity system. As Stoller puts it, utilities are “truly paid to fritter away money, to gold-plate and waste.” And, if that’s not bad enough, in some states these same utilities can spend your money on political activities.

According to the Energy and Policy Institute, in states where laws prohibit utilities from charging customers for political spending, consumers are saving hundreds of millions of dollars a year.

Meanwhile, you, the average customer, are sitting around believing that paying more will lead to a better grid. That is the implicit bargain behind every rate increase. Customers are told that higher bills today will lead to a more reliable system tomorrow. Yet the opposite complaint seems to be growing louder every year.

The federal organizations responsible for monitoring the nation’s electric system have repeatedly warned that large portions of the country face increasing blackout risks as power demand grows and existing infrastructure ages.

Ultimately, the problem is that the system rewards spending itself: A utility that finds a cheaper solution earns less, and a utility that spends billions building — not fixing — infrastructure earns more.

As Stoller puts it, “They are willing to waste $1,000 to send an extra $60 to shareholders.”

Many experts argue that one of the most effective ways to lower costs and improve reliability would be to build more high-voltage transmission lines connecting different regions of the country.

Think of the electric grid as a national marketplace. Some regions have abundant, inexpensive electricity. The Great Plains, for example, have some of the world’s best wind resources. The Southwest has enormous solar potential. Other regions, particularly dense population centers in the Northeast and parts of the Midwest, often face higher electricity costs and tighter supply constraints.

The obvious solution is to move more power between these regions. Done correctly, these projects can lower costs, improve reliability and make the entire system more resilient.

But that requires coordination. Large interstate transmission projects involve multiple states and multiple regulators, more oversight. And crucially, they don’t fit as neatly into the business model that rewards individual utilities for expanding their own assets.

As a result, utilities favor smaller local projects that are easier to approve, easier to build and guaranteed to generate shareholder returns.

Other countries have moved far more aggressively to build long-distance infrastructure capable of moving power across vast regions. Look at China, which has built more than 8,200 miles of high-voltage transmission lines in recent years. The U.S. has built a mere 375.

At this point, you may be wondering: Where are the regulators? After all, utilities don’t operate in a free market. Customers can’t simply switch providers when rates rise.

The entire justification for granting utilities monopoly status is that government regulators are supposed to act on behalf of the public. In theory, that’s the safeguard. In the real world, that has become part of the problem.

Consider a recent example in Pennsylvania. When the Pennsylvania utility PECO — a subsidiary of Exelon, the largest utility in the country — recently asked for a return of nearly 11%, far above the national average, it took the governor publicly shaming them to get it withdrawn.


Customers are told that higher bills today will lead to a more reliable system tomorrow. Yet the opposite complaint seems to be growing louder every year.

Democratic Gov. Josh Shapiro called PECO’s proposed rate hike “pure greed.” In response, PECO said in a statement that the company “shares Governor Shapiro’s concerns about affordability and remains focused on keeping customer bills as low as possible while continuing to invest in safe and reliable service.”

The rising costs led Shapiro to launch a new watchdog to scrutinize utility profits.

But critics argue that many of the state commissions that are supposed to oversee these utilities have been effectively captured. The revolving door between regulators and utility companies means that today’s watchdog can become tomorrow’s utility executive, and vice versa.

At the same time, utility companies are often permitted to contribute money to the campaigns of officials involved in overseeing them. The result is regulatory capture, with the system increasingly serving the interests of the companies rather than the ratepayers it was designed to protect.

That’s why the industry’s response to virtually every challenge sounds so familiar. Need to strengthen the grid against storms? More spending. Need to accommodate renewable energy? More spending. Need to support artificial intelligence data centers? More spending. Need to improve reliability? More spending. And systems rarely reform themselves when the people involved are benefiting from the status quo.

Most Americans don’t understand the mechanics of rate bases, transmission planning or regulatory capture. They don’t need to. What they understand is that their bills keep rising. They understand that every year seems to bring a new explanation for why prices have to go up again.

For much of the 20th century, utilities were largely run by engineers. Their mission was straightforward: keep the lights on. Today, the system is run by financial engineers focused on returns on their investments.

Allison Detzel contributed.

The post Americans’ electric bills are skyrocketing as utilities rake in record profits appeared first on MS NOW.

Dell high-end lightweight laptops costing $3,000


Dell’s Massive XPS Price Hikes Spell the Doom of Cheap PCs
Welcome to the age of high-end lightweight laptops costing $3,000 or more.
BY KYLE BARRPUBLISHED MAY 18, 2026, 2:15 PM ET

READING TIME 2 MINUTES

The Dell XPS 16 now costs nearly 20% more than it did a few weeks ago. © Raymond Wong; Gizmodo composite
READ LATER COMMENTS (10)



No laptop can escape the plague of spiking RAM prices. In what feels like a watershed moment for notebooks everywhere, Dell’s longtime high-end XPS laptops now cost close to or more than $3,000 if you want the latest and greatest specs and screen.

The company’s revised XPS 14 and XPS 16 models were supposed to help get the company’s notebook brands back on track. Now, these already expensive laptops cost nearly 25% more. When we first reviewed the XPS 14, it cost $2,200 for the high-end model that comes with an Intel Core Ultra X7 358H chip, 32GB of RAM, and the OLED touch display. Now, as of May 18, the laptop costs $2,900 at Best Buy. An XPS 16 came with a $2,350 price tag when Gizmodo reviewed it this month. Now, it’s $2,950.

These laptops cost even more on Dell’s own webstore (these laptops also come with limited game and creative software bundles when ordering direct from Dell). Those prices are not even the highest-end version of the laptops. There are additional configurations with a higher-end Intel Core X9 388H that cost $3,000 at 14 inches and $3,050 at 16 inches. Overall, Dell’s new pricing scheme for its longtime XPS laptop lineup feels more like our PC-loving brains are being pile-driven into hard concrete.


There is one non-OLED version of the XPS 16 with the same chip that currently costs $2,480 on Dell’s online storefront. In an email, a Dell spokesperson confirmed that these were indeed the new prices of its 2026 XPS models, adding, “It has been a dynamic time in our industry for component costs along with other factors.”

Just two years ago, you could expect to grab a decently powerful gaming laptop with an OLED screen and a discrete GPU for under $3,000. In 2026, Dell’s beloved Alienware brand now hopes to sell an Alienware 15 “budget” laptop starting at $1,300 for the lowest-end configuration and costing $2,300 with a higher-end GPU and 32GB of RAM.

Essentially, the pricing scheme consumers had come to expect for all PCs is getting thrown out the window. Fellow PC maker Lenovo recently spiked the price of its Legion Go 2 gaming handheld to $2,000. More device makers are actively considering scaling back the capabilities of their gadgets in order to keep prices steady, a process best described as “shrinkflation.”

Gizmodo was pretty positive about Dell’s redesigned XPS models. They featured bright, beautiful OLED displays, strong performance with Intel’s latest Core Ultra Series 3 chips, and a high-quality chassis. Sure, their seamless keyboards grew increasingly annoying to type on, but they at least captured their own unique look in a world full of dull, gray boxes.

Are either of these laptops worth close to $3,000? It may not matter anymore. Soon, more and more PCs may hike costs to compensate for the ballooning prices of RAM and other memory components.

RG Richardson Communications News

I am a business economist with interests in international trade worldwide through politics, money and banking. Interactive Internet VoIP and secure eMail Communications. The author of RG Richardson City Guides has over 300 guides, including restaurants and finance.