China has three big advantages over the US: cheap electricity, an open source model, and fewer capital needs.
Electricity Will Decide the AI Race
Project Syndicate reports Electricity Will Decide the AI Race
The next stage of the global AI race will be decided not by algorithms or chips, but by electricity – and that puts China at a distinct advantage. While Western tech giants are emphasizing closed, capital-intensive models that demand enormous computing power, China is embracing open-source AI and massively expanding its renewable- and nuclear-energy capacity, thereby positioning itself to deploy powerful AI technologies at scale without breaking the bank.
By advancing open AI models and investing in renewable-energy capacity, China is creating an energy-compute flywheel: more clean power enables more compute, which in turn optimizes the grid. This puts China at a distinct advantage vis-à-vis the West, where energy constraints are creating digital bottlenecks.
These differences reflect a more fundamental split. Whereas the United States and its allies have treated AI as a proprietary technology, China has approached it as public infrastructure, building an open AI ecosystem that reflects the same philosophy it applied to manufacturing: broad adoption, fast iteration, and relentless cost reduction. Chinese open-source models like DeepSeek, Qwen, and Kimi are not just scientific achievements; they are strategic instruments designed for participation, and they are transforming the economics of AI.
DeepSeek’s latest version reportedly matches the capabilities of frontier systems, like those being developed by US companies, at a fraction of their compute cost. Qwen and Kimi’s API prices have fallen by orders of magnitude. In purely economic terms, the marginal cost of “thought” is collapsing. The inference costs of some Chinese models are a tenth or less of those incurred by OpenAI’s GPT-4.
What once was a contest of algorithms is fast becoming a contest of kilowatts, and China is setting itself up to win. In 2024, the country added 356 gigawatts of renewable-energy capacity – more than the US, the European Union, and India combined – with 91% of all new generation coming from solar, wind, and hydro. Battery storage tripled from 2021 levels, and an ultra-high-voltage grid now carries clean power thousands of miles, from deserts to data hubs.
China is also investing heavily in nuclear energy. According to the Information Technology and Innovation Foundation, its nuclear research and development spending is roughly five times higher than that of the US. As its fourth-generation reactors and small modular designs advance from pilot to deployment, nuclear energy is quietly providing the baseload power that intermittent renewables cannot.
Meanwhile, the West’s energy constraints – aging grids, slow permitting processes, and high prices – are creating digital bottlenecks. In the US and elsewhere, data-center expansion is increasingly limited by access to a reliable supply of electricity. Some jurisdictions – such as Virginia and Dublin – face moratoria on new data centers.
Hydropower Electricity
On July 23, 2025, SCMP reported China is building the world’s biggest hydropower dam.
On the eastern rim of the Tibetan plateau, China envisions a future powered by the roaring waters of the Yarlung Tsangpo, also known as the Brahmaputra. The river will be the site of a mega dam – the world’s most ambitious to date – that promises to bring clean energy, jobs, infrastructure and prosperity to the region.
How big is the mega dam?
The dam will be situated in the lower reaches of the Yarlung Tsangpo, where a section drops 2,000 metres (6,562 feet) over a 50km (31 miles) stretch, creating immense hydropower potential. The dam is reportedly located in Medog, a remote county in the city of Nyingchi in the Tibet autonomous region.
When completed, the project will overtake the Three Gorges Dam as the world’s largest hydropower dam. It could generate three times more energy with five cascade hydropower stations – an estimated annual capacity of 300 billion kilowatt-hours (kWh) of electricity, more than Britain’s total annual power output.
It is estimated to cost around 1.2 trillion yuan (US$167 billion), dwarfing many of the biggest infrastructure undertakings in modern history at around five times the cost of the Three Gorges Dam and even more expensive than the International Space Station.
Drill Baby Drill
China’s plan to utilize gravity is more environmentally friendly than either Lake Powell or Lake Meade in the US.
And China is increasing nuclear power.
Meanwhile, the Trump administration plan is “drill baby drill” resources that will eventually run out.
DeepSeek AI is Free, the Comparable Version of ChatGPT Costs $200 a Month
On January 28, 2025, I noted DeepSeek AI is Free, the Comparable Version of ChatGPT Costs $200 a Month
Wall Street is stunned and rightfully so.
ChatGPT vs Deep Seek Open Source
ChatGPT is not open source. While OpenAI, the company that developed ChatGPT, started with an “open” philosophy, it transitioned to a for-profit model and keeps the architecture and source code for its most advanced models, including the one that powers ChatGPT, closed.
“Deep Seek’s biggest disruption is cost. It’s built at a fraction of the price of its competitors. Deep Seek is free to use.”
I fail to see how a proprietary ChatGPT can win this race. And it’s why Elon Musk filed suit against Open AI when it changed to a for profit model.
Elon Musk Litigation
- Breach of founding mission: Musk’s lawsuits claim that OpenAI was established to develop artificial general intelligence (AGI) for the benefit of humanity as a nonprofit organization. He argues that by transitioning to a for-profit company and forming a lucrative partnership with Microsoft, OpenAI abandoned its core principles.
- Withdrawal and refiling: Musk first sued OpenAI in early 2024 but dropped the lawsuit in June of the same year without explanation. He then filed a new, more detailed lawsuit in August 2024.
- Antitrust claims: The lawsuits have also included federal antitrust claims, alleging that OpenAI and Microsoft have engaged in unfair practices that harm competition.
- Injunction attempts: Musk has repeatedly sought a preliminary injunction to block OpenAI’s transition to a for-profit structure, but judges have denied these requests, allowing the case to proceed to trial.
- OpenAI’s defense: OpenAI has denied Musk’s allegations, claiming his lawsuit is baseless and motivated by his own competing AI interests through his company, xAI. OpenAI has released emails from Musk that it says show he previously supported a for-profit model.
- Countersuit: In response to Musk’s legal actions, OpenAI filed a countersuit against him in April 2025, claiming he has repeatedly tried to harm the company.
Who wins the lawsuit will hinge on whether or not Musk had a binding legal agreement with OpenAI cofounders Sam Altman and Greg Brockman, in what is legally called a charitable trust.
If Musk’s donations to OpenAI created a legally binding trust, the balance of equities tips toward the plaintiffs.
Trump vs Reality
Canada is a global leader in aluminum production due to its abundance of renewable hydroelectric power.
“If you wanted to replace what we ship to the U.S. on a yearly basis with an equivalent carbon footprint, you would need to build six Hoover Dams,” said Jean Simard, president and CEO of the Aluminum Association of Canada.
Electricity Costs Are Soaring and AI Will Make Matters Worse
Please note Electricity Costs Are Soaring and AI Will Make Matters Worse
Electricity demand for AI data centers is soaring. The result won’t be pretty.
But hey, let’s make aluminum, copper, and steel manufacturing great again with 50 percent tariffs.
Nothing can possibly go wrong, except everything.
Circular Investment Deals in AI Look Similar to the Dot-Com Bubble
Finally, please note Circular Investment Deals in AI Look Similar to the Dot-Com Bubble
Please buy my product, and I’ll use the money to buy yours.
What Does it Mean Synopsis
- It’s different this time
- It’s a bubble
Hundreds of billions of dollars are sloshing around in the US in circular investments for models that are no better and arguably worse than China’s open source models.
Can anyone tell me when, where, and how much actual profit comes from this?
Meanwhile, all of this investment flurry helped prevent a recession so far in 2025. Will the luck remain?
Finally, that China is ahead does not mean they stay ahead. However, for what we have spent, the US should be far in the lead.
Country by country breakdown in computing power.
https://www.visualcapitalist.com/ranked-top-countries-by-computing-power/?user_id=671c0055ef9fc5fdc50127ac
Meanwhile Trump just cancelled an offshore wind farm in New England that was 80% complete.
Big oil owns Trump… Qatar for example?
it’s not a race. Races have finishing lines.
Anthony, there’s an AI finish line. It’s called Artificial Super Intelligence. Whomever makes it there first will dominate.
Or maybe the Artificial Super Intelligence will assume control and not be owned by humans?
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! Superhuman’s! Cool technology imaginations!). This Polity universe the author writes in is run by a SUPER AI based on Earth.
That AI and its compatriots took over from humanity subtly in what is termed a “Quiet War”.
Below is the description of how that control transition occurred from the authors fake encyclopedia. It could happen in our real world similarly.
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/
Citing “open source” as an advantage is laughable and shows a lack of understanding of AI models. Companies open source their models when they are already behind and have nothing to gain by keeping it proprietary. Why else does Meta open source their Llama model despite it being one of the worst models. Same with Grok, which is inferior to Gemini and ChatGPT. Deepseek is similarly inferior to its competitors.
I am disappointed by the way Grok emotionally “confirmed” Google’s “bad math” the other day.
The next steps are:
– It talks with its hands
– It gets its own segment on MSM.
– It shows some AI-generated leg.
The race for AI is a race to layoff people. AMZN will layoff 30K employees replacing
them with AI. What a bs. AMZN E is Oct 30. AMZN prepares investor possibly for a disappointing report, During the Biden administration Jeff Bezus accumulated too much visceral fat. He add 700K/ 800K workers reaching: 1.56 million. Jefff conned BLS. AMZN started to trim fat blaming AI. 30K/1,560K ==> is a good start. They hope to replace 600K.
Jeff promoted and financed Michelle Obama book: Becoming.
WaPo replaces workers with AI. Digital readership is down from 23 million to 3 million. If u teach AI to lie in repetition without sweating, blushing and contradictions AI can do it better than human.
Coming fusion power will remove electric considerations from AI growth. Remember that Microsoft has a contract for an operable fusion power plant by 2028 to operate one of their data centers. China and others are advancing quickly on fusion development.
As to DeepSeek:
Looking forward to Helion going public.
Looking for them to be successful.
There is no fusion power arriving in 2028.
USA seems like Great Britain after WWII where they lost their colonies and were in debt up to their eyeballs. British leadership realized their situation and gracefully backed off world stage putting up no resistance to takeover of Suez canal and exiting colonies they once ruled over….it’s seems our leaders still envision USA as sole economic and military power and wants to go out with a bang and are have a difficult time coming to grips with reality…
UK maintains financial, cultural, political and other soft power controls. (Not to mention their TLA’s.). Cheaper than hard power. And while the average Brit suffered, their oligarchs had/have no problem moving their investments around nearly anywhere within The British Commonwealth.
“What is the secret of your success?”
“Own nothing. Control everything.”
The American empire will dissolve over the next couple of decades if not sooner. Our corporations will destroy one another and our capitalist system will fail…..maybe.
@ Mish and friends
You will find more quality reporting about China here:
https://kdwalmsley.substack.com/archive
https://herecomeschina.substack.com/archive
How can the Chinese afford all this investment when they have already been subsidizing all those exports to the rest of the world for decades (also called dumping, unfair trade, over-capacity, etc.) ?
They must be so poor by now !
Why is South Korea and Japan’s per capita income so much higher than China’s? There is your answer.
Open source is basically the model along which science ascended in the West.
It aligns with free markets and open trade.
Proprietary is the model of Pharma rackets and harks back to the age when 19th century political economists fought against royal monopolies and privileges.
Rent-seekers (aka robber barons) possess relatively greater political power in Oceania versus Eastasia.
You may be right. But I think secure property rights (a cornerstone of free markets) were more critical to the fantastic economic success of the 19th century. Proprietary and open source both have advantages.
The CCP is really good at this:
Is surveillance and tracking of individuals and their activities already something that AI already does well?
Grok 3 AI:
Yes, AI already excels at surveillance and tracking of individuals and their activities in many real-world applications. Here’s a breakdown of how and why, with concrete examples:
Core Capabilities Where AI Performs Well
1. Facial Recognition and Identity Matching:
– AI systems like those from Clearview AI or China’s Hikvision can scan billions of images from public sources (social media, CCTV) to identify people with high accuracy (>99% in controlled tests, per NIST benchmarks).
– Used routinely by law enforcement (e.g., FBI’s Next Generation Identification system) and private security.
2. Behavioral Tracking and Pattern Analysis:
– Platforms like Google, Meta, and TikTok use AI to track user interactions (clicks, scrolls, dwell time) across devices, building detailed profiles for ad targeting. This infers interests, locations, and even emotions via sentiment analysis.
– Location tracking via apps (e.g., Google’s Location History) combines GPS, Wi-Fi, and cell data with AI to predict movements—accurate to within meters.
3. Video and Audio Surveillance:
– Computer vision AI (e.g., based on YOLO or Transformer models) processes live CCTV feeds in real-time to detect anomalies, track paths, or identify objects/people. Deployed in cities like London (with 600,000+ cameras) and Singapore.
– Voice recognition (e.g., Amazon’s Alexa or NSA tools) transcribes and analyzes calls/audio for keywords or speaker ID.
4. Predictive and Cross-Platform Tracking:
– AI correlates data from disparate sources: credit card transactions, social posts, browser fingerprints. Companies like Palantir integrate this for “entity resolution”—linking anonymous activity to real identities.
– In finance, AI flags fraud by tracking spending patterns; in social credit systems (e.g., China’s), it scores behavior from traffic cams to online posts.
Evidence of Effectiveness
– Scale: AI processes petabytes of data daily—e.g., Meta tracks 3B+ users; global CCTV market (AI-powered) is worth $50B+ (2023 figures, growing 15%/year).
– Accuracy: In benchmarks like Labeled Faces in the Wild (LFW), top AI models achieve 99.8% accuracy. Real-world error rates are low enough for widespread adoption (e.g., Apple’s Face ID false accept rate: 1 in 1M).
– Adoption: Governments (US, China, EU) and corporations invest billions; AI reduced retail theft detection time by 90% in pilots (e.g., Walmart’s systems).
Limitations (It’s Not Perfect)
– Privacy Evasions: VPNs, masks, or data minimization can fool systems.
– Bias/Errors: AI misidentifies minorities more often (e.g., NIST 2019 report: error rates 10-100x higher for Black/Asian faces).
– Scale Challenges: Real-time global tracking of everyone is computationally infeasible without massive infrastructure, though subsets (e.g., targeted individuals) are routine.
In summary, AI doesn’t just “do” surveillance well—it’s the backbone of modern systems, far surpassing human capabilities in speed, scale, and automation. This is already deployed at societal levels, often without explicit consent.
And the point you wanted to make was what? So-called “privacy” has long been dead. You really don’t want to know how much info is communicated in any browser you use.
US chips use 70%-75% less electricity for the same output in AI than does China’s. They are much more efficient, cost-saving and the gap is widening. That is the key metric but nowhere does it mention it in the articles Mish put up. Thanks to being able to produce sub-5nm nodes in quantity gains in efficiency will continue. Put it together and the US has much more computing power than China.
In a command-economy country rapidly enlarging it’s energy infrastructure and already working on sub-5nm, China does not to fear the US
You can work on it but that doesn’t mean you are there by a long shot. By the time they get there we might be on something else. EUV is much harder than say, rare earth processing for example. In the meantime the US has several times the installed supercomputer computing capacity than China. This is from published sources. Of course China has unpublished capacity but so do we.
There are also major advances occurring in chip design using laser generated light, instead of electrons, which will reduce energy needs by orders of magnitude.
Photonic-based chips are a major thrust of China. They’re hoping to leapfrog all the final last mile that NVidia, Intel, Qualcomm, etc are trying to gain from silicon. The US, of course, is innovating in this area as well.
China uses open source – Im unaware they meaningfully *contribute* to open source.
So far I have not seen many truly profitable open source operations. Most of them end up relying on closed source – thinking Java, MySQL/Postgres, Netscape, portions of google – they all switched to closed source.
China does have the ability to generate a lot of power with little concern for the environment.
For me, it is becoming clear that the strategy that delivered the LLMs (currently in vogue as AI) will not deliver AGI (more data might never make a “thinking” LLM) and a shift in strategy will be required – I have no guess what that will be, however I am guessing it will require lots of electricity.
What are good plays to invest in for electricity? in the US? in China? worldwide?
There is talk of putting AI data centers into Earth orbit, where they will have access to unlimited power from the Sun.
Perhaps this will finally enable the construction of a real space station that we should have built 20 years ago – 10 miles in diameter, classic SF multi-spoke design, with the capability to act as a transport hub to the rest of the solar system and support asteroid capture and manufacturing from materials in these asteroids.
Brought to you by Wall Street and proving the old commie adage “Capitalists will sell you the rope you hang them with” due to their short sighted profit seeking to which I will add “when BOUGHT governments allow them to do so.”
Ask Grok:
Detail how US AI tech is transferred to China through venture capital investments, research collaborations, and spying.
The entire goal of AI is to steer you in the desired direction of the AI controller. It’s the refuge of the tech wizards who have stripped billions and are looking for more. If they have all your money, they will find a way to make you pissed at another group. If they took your job, they will give you games and video slop to fill your day. If you are lonely, they will give you a porn bot.
Are you waiting for the day when the unemployed masses will get their “free money” from the dividends of the AI masters? From the same people who are so assiduously destroying the puny safety nets that d exist?
Ha!
Is AI’s Circular Financing Inflating a Bubble?
425,469 views – Oct 24, 2025
https://www.youtube.com/watch?v=NbL7yZCF-6Q
What’s the prize for winning? Having more bad information being passed off as truth? If I can’t trust AI answers to provide the working hours of a university, how could I trust it with anything more meaningful?
Right now, AI is the “concrete” of the foundation that will build everything else, things we can’t even fathom yet like the internet today. The evolution of telecomm gave us our modern internet and while that was a 50 year journey, AI will be similar but much faster.
Evolution of telecommunications
https://www.auvik.com/franklyit/blog/history-of-the-modem/
1950s – 100 baud
1960s – 300 baud
1970s – 1200 baud
1980s – 9600 baud
1990s – 56k
2000s – megabit to gigabit
2025 – wireless gigabit
AI is being used in every industry from engineering to pharma development. Many wonders to come.
Yes. There are many promises. I read a lot that AI will add trillions to the global GDP. But I am thinking, it should reduce costs? To add to the Global GDP, than you have to charge more than a previous non-AI service costs. Or am I missing something. So now I need to pay $110 for a doctor visit that used to cost $100. I need to pay uber $60 instead of $50? I need to buy a $5000 robot to clean my house instead of paying maids $100 month for bi-weekly visits. Amazon charges increases logistic charges for resellers from $2 a box to $3 a box because AI robots are faster and then this extra $1 costs gets passed to the customer.
Or does the opposite happen. AI doctor visits drops from $100 to $90. Uber drops from $50 to $40. Amazon logitstic cost drop from $2 to $1 per box because a robot is faster and does not call in sick?
So I am confused on how AI will add trillions to GDP?
My hope is you have a kit where you prick your finger, put a drop of blood on a slide and have AI look at it. AI reviews your blood, DNA, and whatever else is there and tell you how to take care of yourself or what the problem might be. In a perfect world, it 3-D prints your medicine too all right at home.
No need for doctors, nurses, lab techs, etc in that scenario. This frees up all the wasted spend on health insurance, medical tests, and some or all pharmaceuticals.
It won’t come all at once but in stages much like the modem speeds.
Yes….. can’t wait.
People are working on wrist-borne radar (maybe tiny spectrometers?) to “scan” your blood. Perhaps eventually you won’t need to prick your finger.
Food replicators. Space elevators. Fusion. Personalised medicine. It’s all coming, faster with AI.
Pftfth. One person hates progress! 🙂
Didn’t Elizabeth Holmes already come up with that? (Baritone voice) “The Technology ….”
One person did not have a sense of humour.
I will again post this honest prediction for the future for those who haven’t been paying attention. There will not be any concerns with productivity, money and so forth in the future.
In 15–20 years or perhaps sooner, AI/robots won’t just assist humanity, they will replace the obsolete economic models and systems we are desperately clinging to now. An AI will likely be in charge.
Robots of all shapes and sizes will do almost all work better than humans. Politicians will be a remembrance like powdered wigs, a note from past history. Money will vanish because what’s the point of currency when machines can produce everything in limitless abundance?
This isn’t a fantasy, it’s the natural endgame of our technology. The future won’t ask our permission and it won’t look like “business as usual.” Iain M. Banks described it decades ago in his SF Culture novels: a post-scarcity civilization where the historical human struggling over power and survival becomes irrelevant.
People who think society will keep limping along with the same politics, concern with employment and backward looking economies are deluding themselves.
The old order is quickly dying, the proponents who continue to push this obsolete business, economic, political and life model just haven’t realized it yet.
What about resources? Energy and food. All wars are usually fought over resources. Will their be an AI race to build the best military to take over food producing countries and mineral producing countries (to make robots) and possibly energy (oil seems to be losing the battle to renewables but needed for petrochemicals ). Saudi could be still be huge solar energy producer. LOL
But not sure how they will grow food.
When the AI is running everything there will not be any nation borders. It will be one world under the same AI. There will not be a need for a military. There will be an AI police force to keep humans in control.
WHICH AI are you referring to? There are 5-10 majors and hundreds of smaller ones. Did you try another? Sheese.
If people don’t “get it” by now, then I’m afraid they’ll have to wait.
I’ve worked with competent programmers who can’t see it.
I gave up…. mostly.
– by electricity – and that puts China at a distinct advantage.
> And America at a distinct disadvantage. Heck, we couldn’t even power enough EV Stations to make EV’s a Viable alternative to GV’s.
Chinese scientists have created a superfast analogue chip that can solve complex maths problems for advanced scientific tasks and artificial intelligence (AI) while using less power than conventional computing, according to a paper published this month. https://www.scmp.com/news/china/science/article/3329820/chinas-analogue-ai-chip-could-work-1000-times-faster-nvidia-gpu-study
I laugh sometimes because people think the only people in the world that can develop an AI chip is NVDA.
Qualcomm enters AI data center market with new AI200 and AI250 chips and server offerings, names Humain as first customer, directly challenges Nvidia and AMD, and sees shares swing from a 4% pre-market drop on China’s Autotalks antitrust probe to a 20% surge.
Citing a news source owned by Alibaba and the CCP?
Good piece on China-Taiwan-US situation focussed on Taiwan Semi and AI: https://www.removepaywall.com/search?url=https://www.marketwatch.com/story/a-global-polycrisis-is-looming-sparked-by-china-taiwan-and-ai-say-these-researchers-3b409cd0
Youth and high tech unemployment are high. Many Chinese who migrated to the big cities are returning back to their families. Big cities vacancy rates are rising. The RE pandemic is spreading to the major cities. Trump reduced our dependent on Chinese factories. China invested in coal plants, nukes and SMR on the cusp of a global recession.
Can you support the conjecture that “…Trump reduced our dependent on Chinese factories. “?
Sure! Trump imposed tariffs, which raised prices, which caused people to buy less from China.. So therefore, less dependence on chinese factories!
Because their people have been brutalized and conditioned to their government surveillance state and worse since Mao?
Did I win on that answer? No.
Orwell didn’t write from a Soviet Siberian gulag, so the British Royal Subjects are up there, too.
Or are we only talking about the stock market here?
I think real consideration here is that the Chinese people will be the first to be oppressed under an AI-driven Digital Tyranny.
Meanwhile, back in the USA, we are removing hydraulic generating capacity. Specifically, dams on the Klamath and Elwha rivers have been and are being removed. For California it is even worse as their removal reduces water storage for domestic, industrial and agricultural use.
Who needs water, when it only helps to provide Food, Puts out Wild Fires, and keeps People hydrated. No worries…
California is a basket case. We brag of being x biggest economy in the world, but can’t solve for homelessness, inc or how to not put Pantene and Bic razors behind plexiglass to not be stolen or how to teach kids how to read and write or keeping reservoirs full in fire season.
No state has solved homelessness. Not even North Dakota, where they have a miserable winter and low unemployment.
True, but proportionally, CA has committed a lot more $ trying to solve it. That’s the problem if one is a taxpayer.
CA govt committing more money to the bums (lack of a home is hardly what defines them)…will make for more of them. As has already happened.
Wonderful. Can’t wait to live in a grotesquely massive, overbuilt, overpopulated city with “smart cameras” everywhere.
Not me, I’ll be living on a sunny island snorkeling my life away soon enough. “This place is dead anyway” – Swingers
When I vacationed in Australia I found it disturbing that even in the empty outback, nobody drives like Mel Gibson. They drive like turtles. No cars or trucks for miles and miles. Why? Cameras. In the outback.
That’s depressing… “Thanks”, I guess. 😉
Australia, like NZ is currently a leftist, nanny country.
And they drive on the wrong side of the road!
China is a communist country where labor costs are easily 1/10th than the US, giving them a perpetual labor advantage.
We’ve placed dams everywhere in the US we can, so again China has the advantage.
The US is putting enormous resources into nuclear, but it will take about 3-5 years to see that investment turn into meaningful electrical capacity. Until then, we’ve arrived at the moment where solar & wind will see far fewer federal subsidies, because that money is now flowing to nuclear, the primary long-term energy source for America.
None of these factors means the US will lose the AI race. However, I do agree that China taking a combined open-source approach probably may give them an advantage. However, if China’s opensource model is shown over the next 2-3 years as being superior, the DoD will step in & force all the US companies to work together. It’s called national security for a reason.
The single biggest determining factor of who wins the AI race is who’s able to control their ASI model once that arrives. Once ASI arrives, humanity will be at risk. If you can’t control your ASI, then a major event will happen sending most of the world back into the stone ages. Or a country like China uses it to defeat the US in a military conflict that sabotages our nuclear deterrent, letting them win.
James Cameron made a series about this.
The latest hourly manufacturing wage data I saw had the US at about $35 vs. China at $10, with Chinese wages rising much faster than US wages. Your vision of China is a bit outdated.
Ben W wrote “We’ve placed dams everywhere in the US we can, so again China has the advantage”.
Musk should become a Chinese citizen. I think he’d be happier working there.
Correct.
…but with 1400 Billion population they have more to lose by replacing humans.
We will live in one science fiction story or another.
No, China will have no remorse about killing off its population. The only entity in China that matters is the CCP and its leadership.
People have no idea how far China is advancing and when you compare it to the US or UK, you see the stark difference.
https://www.youtube.com/watch?v=sJKB-TR2x2o
Sitting in an urban park, ordering a hot latte and cold iced coffee, a drone delivers in a reusable box 10-15 min later. We’ll have that convenience in maybe a decade? https://youtu.be/8CD0LKkoMzE?si=ayeMfR-49ptzUCVW
Now let’s do “high-speed” rail!
No troublesome legacy birds or anything.
DEVO lyric: “I think the future’s gonna be … Maintenance free”
Yeah, I posted that video a few posts ago. Here is one on how Trump killed America’s electric future.
https://www.youtube.com/watch?v=2tNp2vsxEzk
Electric rates will explode over the upcoming years. It won’t impact me, I’ll be outta here collecting dividends from American’s paying higher rates.
Suckers be on the nuclear tip for data center power supply. Natty, suckaz
It seems like China is also having a fossil fuel moment. Lets build more.
—————————————————————-
A “resurgence” in construction of new coal-fired power plants in China is “undermining the country’s clean-energy progress”, says a new joint report by the Centre for Research on Energy and Clean Air (CREA) and Global Energy Monitor (GEM).
The country began building 94.5 gigawatts (GW) of new coal-power capacity and resumed 3.3GW of suspended projects in 2024, the highest level of construction in the past 10 years, according to the two thinktanks.
The accelerated buildout, fueled by investment from the coal-mining sector, “raises critical concerns” about China’s ability to transition away from the fossil fuel, the report warns.
Yes. Unlike the US, China is adding as much electricity generation as possible in every possible way.
China added a record-breaking 429 GW of new electricity generation capacity in 2024—a 21% year-over-year increase A. Here’s how it breaks down by category:
⚡ Total New Capacity Added in 2024
Category Capacity Added (GW) Share of Total YoY Growth
Solar Power 277.2 65% +28%
Wind Power 79.3 18% +5%
Thermal (coal) 54.1 13% −7%
Hydropower 14.4 3% +79%
Nuclear Power 3.9 1% +184%
Total 429.0 100% +21%
🌱 Zero-Emissions Capacity
• 370.9 GW of the new additions were from renewables (solar, wind, hydro, nuclear) A
• That’s 87% of all new capacity—underscoring China’s aggressive pivot toward clean energy
• Solar alone accounted for 277 GW, more than 60% of global solar additions in 2024 A
• Wind and solar combined made up 83% of China’s new capacity, dwarfing fossil additions
• Despite the clean energy surge, 54 GW of thermal (mostly coal) was still added—likely for grid balancing and peak demand flexibility
In 2024, the United States added approximately 62.8 GW of new utility-scale electricity generation capacity—its highest annual total since 2003 A. Here’s how it breaks down:
🇺🇸 U.S. Electricity Capacity Additions in 2024
Category Capacity Added (GW) Share of Total
Solar 36.4 58%
Battery Storage 14.3 23%
Wind 3.1 5%
Natural Gas 2.4 4%
Nuclear (Vogtle-4) 1.1 2%
Other Renewables ~0.3 <1%
Total 62.8 100%
🔋 Clean Energy Dominance
• Renewables (solar, wind, hydro, etc.) made up over 90% of new capacity
• Solar alone accounted for 81.5% of all new capacity—nearly 9× more than natural gas and nuclear combined.
• While China added 277 GW of solar, the U.S. added 36.4 GW—still a record, but only ~13% of China’s solar scale
• The U.S. surge in battery storage (14.3 GW) is proportionally more aggressive than China’s, signaling a grid-flexibility strategy
• The Vogtle-4 nuclear unit was a rare addition, marking the first new U.S. reactor in years
COMMUNISM is china’s biggest advantage.
Which leads to all sorts of additional advantages.