Essay by Eric Worrall
Greens have noticed AI is incompatible with their beloved renewable transition. And they don’t like it one bit.
Inside Meta’s fight to change climate reality… all so it can frantically expand a risky AI program
Everyone is ignoring the science on what Meta’s generative AI investment really costs, even though there’s no evidence of a single, significant societal benefit.
KETAN JOSHI
OCT 3, 2025…
Big tech is being pulled in a few directions at once. In the US, where most tech companies are headquartered, cosying up to a fascist, climate-denying government means making hollow, technosolutionist noises about carbon capture and nuclear fusion. But for the rest of the world, and particularly in Europe, climate change still exists. Now that these companies have become existentially dependent on data centre expansionism, required to power generative systems that require far more power to deliver worse results, they have to refresh their greenwashing techniques, and that means eroding measured reality from the ground up.
It is not clear what any of this is meant to actually be for. It was recently revealed that Meta explicitly allows its chatbots to develop “sensual” relationships with children, and offer fabricated medical misinformation. Meta illegally downloaded a torrent of millions of books (including mine), to help train its models. Private chats with chatbots were inadvertently made public, revealing sensitive information. Meta’s chatbots are designed to present as real humans, resulting in the rapid spread of mental health crises and even some tragic deaths.
I am trying to think of a single, substantiated and significant societal benefit of Meta’s generative AI investment, and I am pretty confident that it simply does not exist.
…
If there is a neat through-line in the history of climate activism, it is the ongoing fight to connect human society to physical reality. First, the messy struggle to nurture the acceptance of the basic science of the problem, and more recently, the struggle to get everyone who says they accept the science to at least fucking act like it. With big tech, that struggle continues in the new arena of how we measure and report on who’s committing the worst climate sins.
…
Read more: https://www.crikey.com.au/2025/10/03/meta-climate-change-reality-artificial-intelligence/
You know when greens trotsky out phrases like “cosying up to a fascist, climate-denying government“, I don’t get the sense they feel like winners.
Declaring AI has no societal benefit because of tragic stories of kids mistaking their chatbot for their friend is like declaring automobiles have no societal benefit because sometimes there are automobile accidents which involve children.
I absolutely agree children need to be protected – but you don’t ban automobiles because a handful of children get hurt, you make automobiles safer, to reduce the risk of accidents. Which is what needs to happen to AI chatbots.
Because AI is most definitely worth keeping, despite the harm it sometimes causes. In my own field of software development, AI has created a substantial boost in productivity. Not by replacing programmers, but by providing souped up assistant tools which are actually starting to be useful.
In mathematics and research, AI is contributing significant breakthroughs, like a recent breakthrough in fluid dynamics, which could lead to advances ranging from better aircraft, cheaper sea freight, more efficient oil and gas pipelines, better drug delivery syringes and, yes, improved control of nuclear fusion plasmas.
In biology and genetics, the ability of AI to analyse enormous quantities of raw data is leading to more rapid mapping of how DNA and genetics works, better understanding of cancer and other diseases, new cures for previously intractable medical problems, and in the tantalisingly near future, treatments which could slow ageing and improve quality of life for older people.
Where does META fit into all this? I’m no fan of Zuckerberg, on a number of occasions I think Zuckerberg’s behaviour has been abominable, but META does have a legitimate place in the business ecosystem. A lot of people use META to win business, including a friend whose growing Canadian adventure business uses advanced META features to promote her business. META’s AI investment appears to focus on how users and businesses interact with META – better analysis of marketing and campaign effectiveness, better communication with customers and potential customers, and improved workflows.
Why is author Ketan Joshi so hostile towards Meta AI, and AI in general? Only Ketan knows what is happening in Ketan’s head. But the rant I quoted appears to follow an increasingly familiar playbook of greens who refuse to admit their renewable transition is dead, but who in their hearts know their cause has failed.
Energy guzzling AI is shaping up to be a prime target of green bitterness.
Discover more from Watts Up With That?
Subscribe to get the latest posts sent to your email.
The silver lining in this one is the alarmists won’t win this battle and it will make them look more foolish than they already are. It gives them something to focus on demonizing that most of the world has already accepted. AI isn’t the answer to all our unsolved problems but used correctly will benefit us.
Have not gotten myself 100% onboard with AI… philosophical puzzles to work out.
Therefore, I don’t want to put embarrassing an opponent ahead of making the right choice.
AI is the enemy of an enemy
but are they ultimately my friend?
AI will happen with or without my approval, and I can’t think of what I’ll do different to deal with it. Question is, would my opinion of AI or green be any different if AI and green were on the same team? What if they _are_ on the same team? How would I know?
I’m not aware of any AI platform that’s capable of heuristic learning. Until that happens, they are just sophisticated word-salad machines, too prone to hallucinating.
Hallucinating…how so very wonderful; apparantly AI can lie, too. Just ducky.
AI will be used to optimize your investment portfolio…..others will use it to plunder your investment portfolio. Any info you receive from AI on such decisions will be untrustworthy…
Today’s technology, along with AI, are mostly solutions looking for problems. I suspect, regarding AI, problems will manifest themselves but most other problems are in the mind.
I believe the Green Blob favors wind and solar because weather dependent sources cannot maintain industrial society. The thought of peasant scum having nice things fills them with dread.
The thought of peasant scum having
nicethings fills them with dread.They wouldn’t think that would they?
Will a ‘wealth cap’ help the environment? How inequality is fuelling the climate crisis
The money is the oligarchs to spend, obviously. In the past, most of the money has been wasted on projects which the global warming disaster crowd love and from which they can siphon largess. The diversion of large sums into possibly useful projects is what the NGO crowd hates. That next mansion may not be affordable.
Not so long ago, mere minutes it seems, the Zuckster was stomping on climate realists like Mussolini on steroids. He canceled, he censored, he kicked them to the curb. Total Orwellian Big Brother doublespeak rat in the face mind control perped on the “denialists”.
But now it appears the worm has turned. The Zuckmeier wants kilowatts and he wants them bad. All the caterwauling about the Hotpocalypse is counterproductive to his new billionaire scheme. All of a sudden Zucky likes us, he really likes us.
Well well. How about that. So okay Zuckaroni, we’ll be your pals now. But there’s a catch (there’s always a catch). First, we want some funding Big Guy. A few hundred mil will suffice. Make us whole. WUWT needs a new pair of shoes. You catch our drift? Second, we want you to cancel, censor, de-platform, and doxx the alarmists. Let ’em have it. Stomp on their necks like you did ours. After all, fair is fair.
Then, and only then, we’ll get you some kilowatts. The old fashioned way. Whadayousay? Do we have a deal?
“I am trying to think of a single, substantiated and significant societal benefit of Meta’s
generative AI investment, and I am pretty confident that it simply does not exist.”
_______________________________________________________________________
I am trying to think of a single, substantiated and significant problem caused by increasing Carbon dioxide, and I am pretty confident that there isn’t any.
Netflix. Ice cream sandwiches. Alaskan cruises. There does not have to be a namable effect that any arbitrary person would judge beneficial.
Greens will have to dine on humble pie at some point.
They’re welcome to switch off the Met Office’s mainframes.
The pies are baking in the oven and will be delivered to the Greens by EPA Administer Lee Zeldin after he rescinds the 2009 CO2 Endangerment Finding.
Finally, a (very) little actual data I can add to a discussion. I have an interest in the impact AI data centers are going to have on fossil fuels. I’ve been using Google’s Gemini (and some associated programs they integrate with it) for research. It was very obstinate that FF consumption would plateau in SE Asia and India, and renewables would handle a lot of the load. I started asking questions about the equivalence of solar power plants to CCNG. It specifically used the Villanueva solar facility for that.
This was part of its reply:
“Scale: At 754 MW, Villanueva has a nameplate capacity comparable to or larger than many utility-scale combined-cycle natural gas plants, which typically range from 500 MW to 1,000 MW.”Even I could spot the problem with that comparison. Here are excerpts from the rest of the conversation:
I responded:
“At 754 MW, Villanueva has a nameplate capacity comparable to or larger than many utility-scale combined-cycle natural gas plants, which typically range from 500 MW to 1,000 MW.” Is that not a false comparison since the capacity factor is significantly higher for ccng? humans will be very badly misled.
Got this response:
“You are correct. Simply comparing the nameplate capacity of a solar plant to a natural gas plant without mentioning the capacity factor is highly misleading, and can be seen as a false equivalency. A nameplate comparison alone ignores the fundamental differences in how these technologies operate and provide power to the grid.
Comparison based on annual energy generation
Assuming a 754 MW capacity for both, using typical capacity factors:
Solar plant (Villanueva):Capacity factor: ~25%
Annual energy produced: 754 MW * 8,760 hours/year * 0.25 = ~1.65 TWh
CCGT plant:
Capacity factor: ~60% (a conservative mid-range estimate)Annual energy produced: 754 MW * 8,760 hours/year * 0.60 = ~3.96 TWh As this calculation shows, the natural gas plant generates more than double the amount of electricity per year, even with the same nameplate capacity. This highlights why a simple nameplate comparison is misleading.”
Gemini has facts but no understanding of when and how to apply them. What would a typical investor think if he simply accepted Gemini’s first response? Let the user beware.
Greens seem to be reacting like children who have just discovered Father Christmas doesn’t exist,
==
Re AI:
If the meme/quip 2+2=5 occurs more often than 2+2=4 will AI eventually decide that 2+2 really does = 5 because that is a majority opinion and will therefore become consensus maths?
https://www.climatedepot.com/2025/10/06/ais-reliance-on-fossil-fuels-is-almost-unavoidable-the-ny-times-now-acknowledges-that-unreliable-solar-and-wind-cant-power-data-centers/
The greens don’t know what to do. Gotta love it.
“cosying up to a fascist,,,”
The mirror is reflecting his own position. The left is as fascist as they come.
Wow, this is the first answer from Google:
“an advocate or follower of the right-wing political philosophy or system of fascism:
“he went to Spain to fight against the fascists””Eastern European fascists could win power only with support from the Nazis””
So the party of the evil mustached one was… right wing?
Fascism can be practiced by any party.
Fascism is a form of socialism, where the government tells business what to do. As long as the factory owners follow the governments demands, the government leaves them alone.
As soon as they stop following orders, the government just takes over the plants.
No one seems to understand this any longer. Teaching of history in the US is just as bad as all other subjects.
If you read *all* of Marx you’ll find that there are three phases in moving to communism. Fascism – gov’t control of business and capital. Socialism – gov’t ownership of business and capital. Communism – collective ownership of business and capital. Each phase is supposed to transition into the next with communism as the end game.
The problem is that the actual move to true Communism *never* happens. Getting to Socialism requires a huge bureaucracy. Once that bureaucracy gets control it never releases it. And the bureaucracy always winds up being headed by a dictator, i.e. a strongman. It happens this way *every* time.
Fascism, socialism, and communism are, at the base, *economic* concepts. Anything other than this are social biases propagated by the dictator at the head of the bureaucracy, e.g. Hitler, Maduro, Mussolini, etc.
Those who don’t learn from history are doomed to repeat it. The US has already moved far down the road of fascism with the government controlling business in the smallest details and controlling capital investment in nearly every sector – accompanied by a huge bureaucracy.
Each of these phases are products of the Left, not the right. The US is no different. Those saying they are against fascism *are* the true fasctists!
To the left the syllogism goes something like this.
Those we disagree with are evil.
We disagree with those on the right, therefore those on the right are evil.
Hitler was evil, therefore Hitler was right wing.
To MarkW the syllogism goes something like this.
Those we disagree with are evil.
We disagree with those on the left, therefore those on the left are evil.
Hitler was evil, therefore Hitler was left wing.
Really, squabbling over what labels to affix to your enemies is not conducive to a rational discussion. Derogatory labels (e.g. calling Trump a fascist) provides no useful information about the subject to which the label is applied.
So you’ve said the opposite of each line and pointed out that labels are arbitrary but you left the word destroyed. Does it have a meaning or is it just another one we”ll discard when we’re done with it.
As the Demorats say: “Let’s have a partnership between government and big business.” I suspect this is definition “A” of fascism. Fascism, Socialism, and Communism are just different branches of the same Marxist tree; and that tree is nothing but left wing murderous thugs who use right-wing anarchists to tear down anything that is good. Lets not speak Marxist, left wing jargon. Honest citizens are not right-wing, murderous anarchists are!
“I absolutely agree children need to be protected – but you don’t ban automobiles because a handful of children get hurt, you make automobiles safer, to reduce the risk of accidents. Which is what needs to happen to AI chatbots.”
OK, it’s a lousy metaphor but when cars go too fast they become dangerous, as also all the operations they keep increasing to keep track off. Even us hyperactives have limits and pushing faster may be dangerous, some even in unexpected ways. Cars used to be more similar on the critical inside, now not so much, except more similar on the outside. How much gets done just because it can be, and is faster always more intelligent?
Never used it but we’ve already developed a serious problem with lack of homework and thought. Flying cars were faster, but OK, another lousy? No offense to AI.
Quoting the same search engine that thinks Adolf’s party was right wing: “Motor Vehicle Traffic Crashes are a leading cause of death of children.”
Artificial Intelligence is only slightly better than none at all. I have this opinion because it celebrates a lack of curiosity and introspection and fact-checking. “Just ask AI and never mind” leads to a cascading and compounding of errors. Can’t believe I’m with the greenies on this one.
What if AI starts spitting out truly inconvenient truths about politics history and economics?
“tragic stories of kids mistaking their chatbot for their friend”
Big deal, most children have much more to worry about- like bad schools and bullies and divorced parents. Life is not a bowl of cherries. If a kid mistakes a chatbot for a friend, it’s not the end of the world for them.
Sadly, it can be
Bozzer confesses
Boris: I went too far on net zero
Boris Johnson has admitted he went ‘far too fast’ on net zero when he was PM, conceding he got ‘carried away’ about the idea that renewables could replace fossil fuels – in his most outspoken remarks on a policy he once championed. Crikey!
https://www.spectator.co.uk/article/boris-i-went-too-far-on-net-zero/
He still believes in it.
I can’t see why the last USA presidential election seems to have reframed a global worldview. Maybe the election was a coincident event?
I’ve wondered for most of my life when/whether the obvious false alarm would be acknowledged. I think DT is being used as an excuse to change behavior without owning the error. There have to be consequences for the destruction of the dominant political worldview and the central public education reference since 1988ish (cold war over).
I hope we don’t have to start thinking about “interesting times”.
I think that that election has had worldwide consequences because the current administration has cut funding to the Green Blob and has changed the way US agencies behave (somewhat – it will take time). Coincidentally, the Net Zero implementation ids showing signs of failure to even the least well-educated people, and the 50 years of failed predictions is finally catching up with the Blob. But it was the election of Trump that allowed the failures to finally show up.
“You know when greens trotsky out phrases like “cosying up to a fascist, climate-denying government“, I don’t get the sense they feel like winners.”
Freud wearing a slip?
From the quoted article: “I am trying to think of a single, substantiated and significant societal benefit of Meta’s generative AI investment, and I am pretty confident that it simply does not exist.”
Oh come on now. You seem to have no trouble thinking of and promoting non-existent things, like climate crises. Try harder.
My use of the word “trotsky” might have been intentional ;-).
Ha! I just immediately assumed so!
Yeah, I wasn’t sure, but it works either way.
“First, the messy struggle to nurture the acceptance of the basic science of the problem…”
If you want to know the basic science of the “problem”, go back to 1938. When Callendar proposed to attribute a reported warming trend to emissions of CO2, Simpson and Brunt explained why any such assignment of cause and effect was not possible. They understood energy conversion.
https://wattsupwiththat.com/2025/04/06/open-thread-138/#comment-4058322
And for a current comment to EPA in support of the proposed withdrawal of the 2009 Endangerment Finding, again emphasizing the concept of energy conversion within the general circulation:
https://www.regulations.gov/comment/EPA-HQ-OAR-2025-0194-0305
The Zuckerberg – Musk – Altman – Bezos crowd (no doubt I’ve missed some others) making titanic investments in AI should first re-evaluate their understanding of the “problem.” There is no climate problem. There never was a crisis, not even the slightest tendency, driven by emissions of CO2. Confess to the misconception and move on.
Thank you for your attention to this matter.
And here’s the unmistakable admission of a true religion in action –
Bless me Greta, for I have sinned?
Greta’s too busy with the next crisis.
I wonder what she’ll be told to campaign about next to avoid being irrelevant?
Who gets to decide what activities benefit society and which do not.
I suspect Ketan thinks that should be Ketan…
But but but…. Apparently AI is going to be the answer to all the problems with renewables!
‘The role of artificial intelligence in accelerating renewable energy adoption for global energy transformation.’
https://www.sciencedirect.com/science/article/pii/S2666519025000950
Ultimately we have no choice but to explore AI, it’s an economic and military arms race, and our enemies are not going to ignore it.
Doubtful, unless it starts to go by the name of Skynet.
I was about to say that too. Given human nature, fallacies, and darkness-AI scares the Hell out of me.
Except the Greens still can’t comprehend there is no renewable transition in the 1st place. Besides, if AI is interfered with, where will they get their sex pictures of Tillie Norwood?
“accept the science “
As soon as you see some climate zealot use that phrase, you know that they have basically ZERO clue about actual science.
It is essentially a “Call to Authority” that they know basically nothing about.
Very nice Eric. It must suck to be the other side. You know they have lost when the best they can come up with is to call us Fascists and other dirty words. I laugh at them. I also laugh that they are turning on AI. I am not enamored with AI but it is entertaining that AI bothers the CAGW clowns.
Agree, even if you have your doubts and can’t think of another reason to love AI, the fact it drives greens nuts and is breaking their renewable transition is enough of a reason to give AI a hug.
Eric Worrall continues with his mindless, fantastical rants.
You mean like yours?
Conrad, make an effort. At least try to entertain us with your explanation for why I am wrong.
Thank you for admitting that you have no arguments, just more mindless insults.
You are mistaken..
The “Mindless Fantastical Rant” was from Ketan Joshi. !
AI and these data centers electricity consumption simply puts green energy investment on notice. Meta understands the competitive environment and reality and business sense will prevail. Renewable is a loser. With over 20+ years, the technology is not self-supporting and without subsidies the business model fails and failing. What a waste of capital and taxpayer funds for a journey down the proverbial rabbit hole. SMR would have been the smarter choice. The stupidity anymore is utterly pathetic.
So much wrong in two sentences:
When has any government, government body, eco-fascist, sceptic, or those on the fence ever denied that climate change exists?
“Carbon capture” – if the original author doesn’t understand the difference between carbon and carbon dioxide, he shouldn’t be preaching to those of us who do.
Really? Does climate change only exist in Europe? In that case, why should the US give a toss about a problem in Europe?
Dipstick.
Copilot AI tells us with respect to the early days of printing presses … “Scribes’ guilds saw printing as a direct threat to their livelihoods. In some cases, they destroyed presses and chased book merchants out of town.
Critics feared that widespread literacy would erode social hierarchies, giving “dangerous ideas” to the lower classes.”
Some things never change.