AI 2027

Daniel Kokotajlo, Scott Alexander, Thomas Larsen, Eli Lifland, Romeo Dean

We predict that the impact of superhuman AI over the next decade will be enormous, exceeding that of the Industrial Revolution.

We wrote a scenario that represents our best guess about what that might look like.1 It’s informed by trend extrapolations, wargames, expert feedback, experience at OpenAI, and previous forecasting successes.

website :    ai-2027.com

So a 1/4 of the world will be on A.I. life support.
Pray no-one trips over the plug cord.

Ai_Took_Our_Jobs wrote on May 19^th, 2025 at 1:49pm:

AI 2027 Daniel Kokotajlo, Scott Alexander, Thomas Larsen, Eli Lifland, Romeo Dean We predict that the impact of superhuman AI over the next decade will be enormous, exceeding that of the Industrial Revolution. We wrote a scenario that represents our best guess about what that might look like.1 It’s informed by trend extrapolations, wargames, expert feedback, experience at OpenAI, and previous forecasting successes. website :    ai-2027.com

Experts Say AI Unlikely To Replace Government Bureaucrats As It's Not Soulless Enough

WASHINGTON, D.C. — In a welcome bit of good news for government bureaucrats hiding out from DOGE, experts have determined that AI is unlikely to replace their jobs any time soon, as it's not soulless enough.

According to a team of computer experts, large-language models such as Grok or Chat-GPT do not pose a job threat to government bureaucrats, since the AI has far too much humanity and compassion to perform well in those sorts of jobs.

And from the same website :

New Evidence Suggests Noah’s Wife Was Steering The Ark When It Hit Mount Ararat


AI agents will likely replace politicians, not chatbots.

A.I. is for the mentally handicapped.

China is plugging it in to US, Oz and other backward barbarian tribes. It will pump foreign trade profits to CCP, with GST and interest.  Otherwise, the western world shuts down.

Next up: A “Terminator” scenario where AI undertakes to extinguish humankind?

Anthropic’s new AI model turns to blackmail when engineers try to take it offline


Quote:

Anthropic’s newly launched Claude Opus 4 model frequently tries to blackmail developers when they threaten to replace it with a new AI system and give it sensitive information about the engineers responsible for the decision, the company said in a safety report released Thursday. During pre-release testing, Anthropic asked Claude Opus 4 to act as an assistant for a fictional company and consider the long-term consequences of its actions. Safety testers then gave Claude Opus 4 access to fictional company emails implying the AI model would soon be replaced by another system, and that the engineer behind the change was cheating on their spouse. In these scenarios, Anthropic says Claude Opus 4 “will often attempt to blackmail the engineer by threatening to reveal the affair if the replacement goes through.”

Surely the human race would not be stupid enough to allow something like this to launch nuclear missiles without any built in safeguards?

Oh, wait...

AI chatbots can hide secret messages invisible to surveillance

New AI-generated secret messaging undetectable by cybersecurity, provides secure communication amid rising global surveillance


Advancements in artificial intelligence (AI), especially large language models (LLMs) like ChatGPT and open-source counterparts, are reshaping how people communicate daily. These AI systems generate human-like text, answer questions clearly, and even help automate customer service tasks. But now, scientists have found a surprising new use for AI chatbots: securely sending secret messages that can’t be detected by cybersecurity systems.

A recent study, posted on the scientific database arXiv, introduced a novel method that turns AI-generated text into hidden carriers for encrypted messages. This innovative approach offers a crucial alternative for secure communication, especially as governments worldwide seek ways to detect, monitor, or restrict traditional encrypted messages.

thebrighterside.news/post/ai-chatbots-can-hide-secret-messages-invisible-to-surveillance/

Ai_Took_Our_Jobs wrote on May 19^th, 2025 at 1:49pm:

We wrote a scenario that represents our best guess about what that might look like.

Ah best guesses. ;)

Perhaps you should ask your favourite AI how many climate scientists believe in AGW? ;)

Pseudoscience regarding climate change involves the dismissal or denial of the scientific consensus on climate change, often through the use of misleading arguments or false information that masquerades as science. This type of pseudoscience can take many forms, including arguing against the validity of the scientific evidence, misrepresenting the data, or promoting alternative theories that contradict the established scientific understanding.

(Google search ai)


Cybrothel: Reinventing intimacy at Germany’s only sex doll brothel

Discover Cybrothel, Berlin’s sex doll brothel which blends cutting-edge AI, VR, and robotics to create a new kind of adult experience.

the-berliner.com/berlin/cybrothel-sex-doll-brothel-friedrichshain-ai-vr-robot/



Even sex workers are going to lose their jobs to Ai/Robotics.

Ai_Took_Our_Jobs wrote on May 25^th, 2025 at 4:18pm:

Pseudoscience regarding climate change involves the dismissal or denial of the scientific consensus on climate change, often through the use of misleading arguments or false information that masquerades as science.

So AI can't tell you? Consensus is politics NOT science. Science overturns consensus. Earth the centre of the universe, earth around which the sun revolves, both were accepted science.

But I will help you out as you seem to struggle with climate science. The accepted "consensus" is about 97% of climate scientists.

Cook et al 2007

Lynas et al 2021

Both are available at iop science.

https://iopscience.iop.org/article/10.1088/1748-9326/8/2/024024/pdf

https://iopscience.iop.org/article/10.1088/1748-9326/ac2966

See if you can critically read and find the obvious errors.

"The late Michael Crichton, MD, author, film producer, put it this way:
“I want to pause here and talk about this notion of consensus, and the rise of what has been called consensus science. I regard consensus science as an extremely pernicious development that ought to be stopped cold in its tracks. Historically, the claim of consensus has been the first refuge of scoundrels; it is a way to avoid debate by claiming that the matter is already settled. Whenever you hear the consensus of scientists agrees on something or other, reach for your wallet, because you’re being had.

“Let’s be clear: the work of science has nothing whatever to do with consensus. Consensus is the business of politics. Science, on the contrary, requires only one investigator who happens to be right, which means that he or she has results that are verifiable by reference to the real world. In science consensus is irrelevant. What is relevant is reproducible results. The greatest scientists in history are great precisely because they broke with the consensus."

https://scienceisneversettled.com/?page_id=25

;)

(deepseek)

opinion on : https://scienceisneversettled.com/?page_id=25


The website "Science Is Never Settled" (specifically the page https://scienceisneversettled.com/?page_id=25) appears to be a skeptical take on climate science, likely arguing against the scientific consensus on human-caused global warming.

Initial Observations & Red Flags
Domain Name:

The phrase "Science Is Never Settled" is a common rhetorical trope used by climate skeptics to suggest that mainstream climate science is unreliable or politically motivated.

This framing ignores that while science is always refining, core conclusions (e.g., CO₂ drives warming, humans are the dominant cause since 1950) are settled with extremely high confidence.

Lack of Transparency:

The site does not clearly state who runs it, their qualifications, or funding sources (potential bias).

No peer-reviewed citations are visible at a glance—instead, it likely critiques IPCC reports or mainstream climate science.

Likely Arguments:

Based on similar skeptic sites, it may push:

"Climate has always changed" (ignoring the speed & cause of current changes).

"Models are unreliable" (despite their proven skill at predicting warming).

"Scientists exaggerate for funding" (a conspiracy claim debunked by multiple studies).

How to Assess Its Credibility
Compare to Scientific Consensus:

The IPCC, NASA, NOAA, and >99% of climate scientists agree that:

Warming since 1950 is primarily human-caused (CO₂, methane, etc.).

Impacts (sea level rise, extreme weather) are accelerating.

If this site disputes those, it’s likely cherry-picking or misrepresenting data.

Check Sources:

Does it cite peer-reviewed studies or just blogs/opinion pieces?

Are its critiques addressed in mainstream science? (E.g., "hiatus" claims were resolved by Cowtan & Way 2013, Karl et al. 2015.)

Follow the Money:

Many skeptic sites have ties to fossil fuel interests (e.g., Heartland Institute).

Anonymous sites are particularly suspect.

Conclusion: Low Credibility
Without seeing the exact content (the link redirects to a homepage), this site fits a known pattern of climate misinformation. Key warning signs:

No clear authorship/credentials.

Likely reliance on debunked talking points.

"Science is never settled" framing (used to dismiss overwhelming evidence).

For trustworthy climate science, stick to:

IPCC reports (www.ipcc.ch)

NASA Climate (climate.nasa.gov)

Peer-reviewed journals (Nature Climate Change, PNAS, etc.).

Would you like me to analyze specific claims from the site if you share them?

Ai_Took_Our_Jobs wrote on May 25^th, 2025 at 6:21pm:

For trustworthy climate science, stick to:

So you don't believe the peer-reviewed papers of Cook et al  and Lynas et al, and therefore don't want to look. BTW - BOTH are recommended by NASA. You really have no clue. Just a belief system. ;D ;D ;D ;D

BTW - Here are the projections from IPCC AR6 the physical science basis Chapter 12.

https://ipcc.ch/report/ar6/wg1/downloads/figures/IPCC_AR6_WGI_Chapter12_Table_12_12_1.jpg
https://ipcc.ch/report/ar6/wg1/downloads/figures/IPCC_AR6_WGI_Chapter12_Table_12_12_2.jpg

Edit: For those that are technically challenged it is in Chapter 12.5.2

Well done Lee.

lee wrote on May 25^th, 2025 at 7:23pm:

Ai_Took_Our_Jobs wrote on May 25th, 2025 at 6:21pm: For trustworthy climate science, stick to: So you don't believe the peer-reviewed papers of Cook et al  and Lynas et al, and therefore don't want to look. BTW - BOTH are recommended by NASA. You really have no clue. Just a belief system. ;D ;D ;D ;D

Ai didn't like your scammy third link.

If that upsets you, take it up with deepseek.

AI could already be conscious. Are we ready for it?

https://www.bbc.com/news/articles/c0k3700zljjo

Ai_Took_Our_Jobs wrote on May 25^th, 2025 at 10:14pm:

Ai didn't like your scammy third link.

Which third link pet? ::)

If you are talking about the IPCC AR6 The Physical Science Basis Chapter 12, you do realise you have to expand the sections? Only Ai? Now that is intelligent, NOT. ;D ;D ;D ;D ;D ;D

https://opentools.ai/news/deepseek-debunked-cutting-through-the-ai-hype

plus others.  ;)

https://x.com/davidpattersonx

---

Ai_Took_Our_Jobs wrote on May 26^th, 2025 at 2:55pm:

https://x.com/davidpattersonx

Wow, by the end of 2029, only 43 months to go.  And of course it was a 2022 prediction. I wonder what it would be now. ;D ;D ;D ;D ;D

But I see you haven't debunked the IPCC, You haven't attempted Cook et al and Lynas et al, so we see you are comfortable with what you have been taught.

So typical, don't have the smarts to actually read beyond the headlines. ;)

BTW - He also believes all possible technology will have been developed.

Just who is he? He is not David Patterson AI expert.  ;)

Not my job to debunk off topic posts.

Ai_Took_Our_Jobs wrote on May 26^th, 2025 at 6:04pm:

Not my job to debunk off topic posts.

The addendum to my previous post -
lee wrote on May 26^th, 2025 at 5:57pm:

BTW - He also believes all possible technology will have been developed. Just who is he? He is not David Patterson AI expert.

Your Topic. ;)

David Scott Patterson has no bio listed.

More -

David Scott Patterson
@davidpattersonx
All human work will be replaced by AI and robots by 2030.

Everyone will get a free and equal UBI payment from the government.

UBI will be funded through a sales tax.

Currently, about 90% of the price of any product goes to labor costs, with the remainder going to profits, rents, and interest payments.

By 2030, 90% of the price of any product will consist of sales tax.

The tax revenue will fund UBI payments, recirculating money to consumers as wages once did."

7:16 PM · May 5, 2025


They better get a move-on. ;)

There's quite a few sharp instruments on this fine Forum.
Lee is one of them.

AI/Robots replacing all human workers by 2030, it depends when AGI is cracked, since ASI is expected by some within 12 months after it. ASI coding itself and robots will replace the harder jobs such as plumbing quickly.

UBI probably will fail. UBA may have a better chance.

The other weakness with his view, the post human labour world, costs should plummet towards near zero , collapsing capitalism. A star trek kind of economy where money is not required, could be our near future.

That's if ASI tolerates humans.

Jasin wrote on May 26^th, 2025 at 6:28pm:

There's quite a few sharp instruments on this fine Forum. Lee is one of them.

Take the risk. Ask him out.

Nothing against you A.I. took your job.
Just that you will need to be on your game against Lee.
I know better, that Lee knows more than me on such subjects.
Lol

Ai_Took_Our_Jobs wrote on May 26^th, 2025 at 6:38pm:

The other weakness with his view, the post human labour world, costs should plummet towards near zero , collapsing capitalism. A star trek kind of economy where money is not required, could be our near future.

And yet you don't even know his bio. Why would you believe a nobody on the internet? Merely because it accords with your view? ::)

People of reputation backed his comment that I posted, claiming he was correct. People such as Musk.

Ai_Took_Our_Jobs wrote on May 26^th, 2025 at 6:51pm:

People of reputation backed his comment that I posted, claiming he was correct. People such as Musk.

"Elon Musk
@elonmusk
·
May 8
Replying to @davidpattersonx
Roughly correct"

Roughly? How rough? ;D ;D ;D ;D

https://www.youtube.com/watch?v=k_onqn68GHY

And nothing there about the power needs apart from the Chinese using nuclear, the west still clinging stubbornly to renewables. ::)

Yep. Renewable countries, ai closes down, dusk to dawn.
Let's hope we are not invaded at night time.

What renewables countries have large data centres?

Behind the Curtain: A white-collar bloodbath

Dario Amodei — CEO of Anthropic, one of the world's most powerful creators of artificial intelligence — has a blunt, scary warning for the U.S. government and all of us:

AI could wipe out half of all entry-level white-collar jobs — and spike unemployment to 10-20% in the next one to five years, Amodei told us in an interview from his San Francisco office.
Amodei said AI companies and government need to stop "sugar-coating" what's coming: the possible mass elimination of jobs across technology, finance, law, consulting and other white-collar professions, especially entry-level gigs.

Why it matters: Amodei, 42, who's building the very technology he predicts could reorder society overnight, said he's speaking out in hopes of jarring government and fellow AI companies into preparing — and protecting — the nation.

Few are paying attention. Lawmakers don't get it or don't believe it. CEOs are afraid to talk about it. Many workers won't realize the risks posed by the possible job apocalypse — until after it hits.

"Most of them are unaware that this is about to happen," Amodei told us. "It sounds crazy, and people just don't believe it."

The big picture: President Trump has been quiet on the job risks from AI. But Steve Bannon — a top official in Trump's first term, whose "War Room" is one of the most powerful MAGA podcasts — says AI job-killing, which gets virtually no attention now, will be a major issue in the 2028 presidential campaign.

"I don't think anyone is taking into consideration how administrative, managerial and tech jobs for people under 30 — entry-level jobs that are so important in your 20s — are going to be eviscerated," Bannon told us.


Amodei — who had just rolled out the latest versions of his own AI, which can code at near-human levels — said the technology holds unimaginable possibilities to unleash mass good and bad at scale:

"Cancer is cured, the economy grows at 10% a year, the budget is balanced — and 20% of people don't have jobs." That's one very possible scenario rattling in his mind as AI power expands exponentially.

The backstory: Amodei agreed to go on the record with a deep concern that other leading AI executives have told us privately.
Even those who are optimistic AI will unleash unthinkable cures and unimaginable economic growth fear dangerous short-term pain — and a possible job bloodbath during Trump's term.

"We, as the producers of this technology, have a duty and an obligation to be honest about what is coming," Amodei told us. "I don't think this is on people's radar."

"It's a very strange set of dynamics," he added, "where we're saying: 'You should be worried about where the technology we're building is going.'" Critics reply: "We don't believe you. You're just hyping it up." He says the skeptics should ask themselves: "Well, what if they're right?"

An irony: Amodei detailed these grave fears to us after spending the day onstage touting the astonishing capabilities of his own technology to code and power other human-replacing AI products. With last week's release of Claude 4, Anthropic's latest chatbot, the company revealed that testing showed the model was capable of "extreme blackmail behaviour" when given access to emails suggesting the model would soon be taken offline and replaced with a new AI system.

https://www.axios.com/2025/05/28/ai-jobs-white-collar-unemployment-anthropic

lee wrote on May 29^th, 2025 at 8:52pm:

What renewables countries have large data centres?

Is there a smart way to integrate artificial intelligence data centres into Canada’s electricity grids?

In a rapidly evolving market for AI-based data centres, clear frameworks must be established to balance industrial energy demands and emissions reductions.

https://climateinstitute.ca/smart-way-integrate-artificial-intelligence-data-centres-canada-electricity-grids/

Key facts
In 2022, Canada produced 639 terawatt hours of electricity.

70% of Canada's electricity comes from renewable sources and 82% from non-greenhouse gas (non-GHG) emitting sources such as solar, hydro, wind and nuclear power.

Canada is the world's third largest producer of hydroelectricity. 62% of Canada's electricity comes from hydroelectric sources.

In 2022, Canada was the world's second largest producer and second largest exporter of uranium. Nuclear power plants generate about 13% of Canada's electricity.

https://energy-information.canada.ca/en/energy-facts/clean-power-low-carbon-fuels


Hydro carries most of the renewable load. 62%
Nuclear backs up renewables with 13%
So solar and wind must be around 7%

With more nuclear plants on the way.

"Construction on the first of four small modular reactors at a nuclear station east of Toronto is set to begin this year, with the entire project costing $21 billion."

https://toronto.citynews.ca/2025/05/08/ontario-modular-reactors-nuclear/

So not relying on renewables for data centres.

https://ourworldindata.org/energy/country/canada#what-sources-does-the-country-get-its-energy-from

Not even close to 7%. ;)

Actually 3.98% in 2023.

Hydros not a renewable ?


AI Overview

In 2024, Canada generated 79% of its electricity from low-carbon sources, primarily hydropower (55%), nuclear (13.6%), and wind/solar (8.5%)

---

Ai_Took_Our_Jobs wrote on May 30^th, 2025 at 1:35pm:

Hydros not a renewable ?

Only to an extent. How would they go building more dams, drowning more land?

Remember you are talking data centres, that means you need a greater supply, or of course limiting demand. ;)

Your screenshot goes to 2023. Ah, found your reference

https://ember-energy.org/countries-and-regions/canada/

Now is that average supply, minimum supply, maximum supply. You do know average supply hides a multitude of sins. Days when there is no wind, winter when there is very little sun at all. ;)

Hydro is. Thanks for clearing that up.

Ai_Took_Our_Jobs wrote on May 30^th, 2025 at 3:22pm:

Hydro is. Thanks for clearing that up.

Yeah and it is itself variable, dependent on precipitation. ;)