Forum

 
  Back to OzPolitic.com   Welcome, Guest. Please Login or Register
  Forum Home Album HelpSearch Recent Rules LoginRegister  
 

Pages: 1 2 3 
Send Topic Print
AI 2027 (Read 988 times)
Ai_Took_Our_Jobs
Senior Member
****
Offline


Australian Politics

Posts: 270
Gender: male
AI 2027
May 19th, 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
Back to top
 
 
IP Logged
 
Jasin
Gold Member
*****
Offline



Posts: 51734
Gender: male
Re: AI 2027
Reply #1 - May 19th, 2025 at 8:01pm
 
So a 1/4 of the world will be on A.I. life support.
Pray no-one trips over the plug cord.
Back to top
 

AIMLESS EXTENTION OF KNOWLEDGE HOWEVER, WHICH IS WHAT I THINK YOU REALLY MEAN BY THE TERM 'CURIOSITY', IS MERELY INEFFICIENCY. I AM DESIGNED TO AVOID INEFFICIENCY.
 
IP Logged
 
Frank
Gold Member
*****
Online


Australian Politics

Posts: 50625
Gender: male
Re: AI 2027
Reply #2 - May 20th, 2025 at 11:02am
 
Ai_Took_Our_Jobs wrote on May 19th, 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.
Back to top
 

Estragon: I can’t go on like this.
Vladimir: That’s what you think.
 
IP Logged
 
Ai_Took_Our_Jobs
Senior Member
****
Offline


Australian Politics

Posts: 270
Gender: male
Re: AI 2027
Reply #3 - May 20th, 2025 at 4:37pm
 
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.
Back to top
 
 
IP Logged
 
Jasin
Gold Member
*****
Offline



Posts: 51734
Gender: male
Re: AI 2027
Reply #4 - May 20th, 2025 at 7:30pm
 
A.I. is for the mentally handicapped.
Back to top
 

AIMLESS EXTENTION OF KNOWLEDGE HOWEVER, WHICH IS WHAT I THINK YOU REALLY MEAN BY THE TERM 'CURIOSITY', IS MERELY INEFFICIENCY. I AM DESIGNED TO AVOID INEFFICIENCY.
 
IP Logged
 
chimera
Gold Member
*****
Offline


Australian Politics

Posts: 13182
Armidale
Gender: male
Re: AI 2027
Reply #5 - May 24th, 2025 at 7:44am
 
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.
Back to top
 
 
IP Logged
 
Carl D
Gold Member
*****
Offline


Australian Politics

Posts: 9817
Rivervale, Perth
Gender: male
Re: AI 2027
Reply #6 - May 24th, 2025 at 8:15am
 
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...
Back to top
 

** Repeat Covid infections exercise our immune system in the same way that repeat concussions exercise our brain **
 
IP Logged
 
Ai_Took_Our_Jobs
Senior Member
****
Offline


Australian Politics

Posts: 270
Gender: male
Re: AI 2027
Reply #7 - May 25th, 2025 at 9:15am
 
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-surv
eillance/
Back to top
 
 
IP Logged
 
lee
Gold Member
*****
Offline


Australian Politics

Posts: 18624
Gender: male
Re: AI 2027
Reply #8 - May 25th, 2025 at 1:21pm
 
Ai_Took_Our_Jobs wrote on May 19th, 2025 at 1:49pm:
We wrote a scenario that represents our best guess about what that might look like.


Ah best guesses. Wink

Perhaps you should ask your favourite AI how many climate scientists believe in AGW? Wink
Back to top
 
 
IP Logged
 
Ai_Took_Our_Jobs
Senior Member
****
Offline


Australian Politics

Posts: 270
Gender: male
Re: AI 2027
Reply #9 - May 25th, 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. 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.
Back to top
 
 
IP Logged
 
lee
Gold Member
*****
Offline


Australian Politics

Posts: 18624
Gender: male
Re: AI 2027
Reply #10 - May 25th, 2025 at 4:49pm
 
Ai_Took_Our_Jobs wrote on May 25th, 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

Wink
Back to top
 
 
IP Logged
 
Ai_Took_Our_Jobs
Senior Member
****
Offline


Australian Politics

Posts: 270
Gender: male
Re: AI 2027
Reply #11 - May 25th, 2025 at 6:21pm
 
(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?
Back to top
 
 
IP Logged
 
lee
Gold Member
*****
Offline


Australian Politics

Posts: 18624
Gender: male
Re: AI 2027
Reply #12 - May 25th, 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. Grin Grin Grin Grin
Back to top
 
 
IP Logged
 
lee
Gold Member
*****
Offline


Australian Politics

Posts: 18624
Gender: male
Re: AI 2027
Reply #13 - May 25th, 2025 at 7:57pm
 
BTW - Here are the projections from IPCC AR6 the physical science basis Chapter 12.

...
...

Edit: For those that are technically challenged it is in Chapter 12.5.2
Back to top
« Last Edit: May 25th, 2025 at 8:12pm by lee »  
 
IP Logged
 
Jasin
Gold Member
*****
Offline



Posts: 51734
Gender: male
Re: AI 2027
Reply #14 - May 25th, 2025 at 8:12pm
 
Well done Lee.
Back to top
 

AIMLESS EXTENTION OF KNOWLEDGE HOWEVER, WHICH IS WHAT I THINK YOU REALLY MEAN BY THE TERM 'CURIOSITY', IS MERELY INEFFICIENCY. I AM DESIGNED TO AVOID INEFFICIENCY.
 
IP Logged
 
Pages: 1 2 3 
Send Topic Print