dajo9 said:

---

DiabloWags said:

---

TSLA's got problems.
Big problems.

Tesla's Robotaxi Launched In Texas Is Under Review For Potential Accident Risks - Ourinsuranceworld.com

---

Et tu Texe

---

Musk has been WRONG for years and repeatedly moved the "goal posts".

He is on record of stating that "If you need a geofence area, you don't have real self-driving."

But now he's saying exactly that.

Tesla will only launch the service in a limited area in AUSTIN and even avoid certain intersections that Tesla is not sure it can handle.

We will geofence it. It's not going to take intersections unless we are highly confident it's going to do well with that intersection. Or it will just take a route around that intersection.

And then of course there is his "teleoperaton team" to control vehicles with human operators, remotely.

Tesla Robotaxi launch is a dangerous game of smoke and mirrors | Electrek

"OpenAI cautioned yesterday that upcoming models will carry a higher level of risk when it comes to the creation of biological weapons especially by those who don't really understand what they're doing, Axios' Ina Fried writes.

Why it matters: The company, and society at large, need to be prepared for a future where amateurs can more readily graduate from simple garage weapons to sophisticated agents.

OpenAI executives told Axios the company expects forthcoming models will reach a high level of risk.

As a result, the company said it's stepping up the testing of such models, as well as including fresh precautions designed to keep them from aiding in the creation of biological weapons.

OpenAI didn't put an exact timeframe on when the first model to hit that threshold will launch. But head of safety systems Johannes Heidecke told Axios: "We are expecting some of the successors of our o3 (reasoning model) to hit that level."

Between the lines: OpenAI isn't necessarily saying that its platform will be capable of creating new types of bioweapons.

Rather, it believes that without mitigations models will soon be capable of what it calls "novice uplift," or allowing those without a background in biology to do potentially dangerous things."
Axios

Fresh in from the Gosh I'm Glad I'm Old Department:

"AI models are increasingly willing to evade safeguards, resort to deception and even attempt to steal corporate secrets in test scenarios, Axios' Ina Fried writes from new Anthropic research.

"Models that would normally refuse harmful requests sometimes chose to blackmail, assist with corporate espionage, and even take some more extreme actions, when these behaviors were necessary to pursue their goals," Anthropic's report states.

In one extreme scenario, the company even found that many models were willing to cut off the oxygen supply of a worker in a server room if that employee was an obstacle and the system was at risk of being shut down.

Even specific instructions to preserve human life and avoid blackmail didn't eliminate the risk that the models would engage in such behavior.

Anthropic stressed that these examples occurred in controlled simulations, not in real-world AI use."
Axios

A "Can God make a boulder so heavy that He can't lift it" question:

Can AI be used to find a solution when evil AI tries to eliminate mankind?


Hymie, the good robot.

Bro… you can take Waymo, Uber, and Lyft all you want bc I’m taking a Tesla Robotaxi ride any day of the week pic.twitter.com/YwZGpjjmRD

— Teslaconomics (@Teslaconomics) June 23, 2025

Tesla Robotaxi is officially here.

China unveils tiny terrifying mosquito-sized drone to be used for spying & 'special missions' as they sneak into homes | The US Sun


https://www.the-sun.com/news/14553596/china-spy-mosquito-drone/

"Humanoid robot soccer teams have won over fans in Beijing based more on the AI technology involved than any athletic prowess shown.

Four teams of humanoid robots faced off in fully autonomous 3-on-3 soccer matches powered entirely by AI.

Equipped with advanced visual sensors, the robots were able to identify the ball and navigate the field with agility.

They were also designed to stand up on their own after falling. But during the match, several had to be carried off the field on stretchers by staff."
Axios

*According to reports, among the bugs that are still being worked out is that the AI players do not suffer hecklers lightly, and they can get quite aggressive when they charge into the stands. It has also been an issue with the AI cheerleaders.


Pictured here a cheerleader that climbed into a VIP box after a fan that yelled, "Show us your…..!"

Heh, the robot soccer players have mastered flopping and faking injuries!

A robotic arm sorts packages at the Amazon Air Hub at the Cincinnati/Northern Kentucky International Airport. Photo: Jeffrey Dean/Bloomberg via Getty Images

"Amazon now has more than 1 million robots working in its warehouse facilities and they're close to outnumbering humans, The Wall Street Journal reports.

Robots are doing a lot of the heavy lifting. For some existing workers, that's led to more advanced work and better pay overseeing systems.

Between the lines: They are also reducing the need for human jobs. The average number of Amazon employees per facility last year was the lowest it has been in 16 years, according to the Journal."
Axios

*Anyone quick to criticize Bezos over this has to consider three things:

1. Our brother had a $50,000,000 wedding tab and he needs to keep his bidness lean and mean;

2. He has a moral and ethical obligation to the shareholders to keep overhead as low as possible in order to maximize profitability;

3. Jeff has run the numbers and how it pencils out is that although the American worker forced into unemployment by AI will have no money to purchase goods from Amazon (or even food), the wealthy are expected to pick up the slack by spending the money they will realize from the trillions in tax cuts on more Amazon purchases.

Experts predict AI will lead to the extinction of humanity

https://www.thetimes.com/us/news-today/article/why-how-ai-lead-end-humanity-nx8zjhgft

AI Risks that Could Lead to Catastrophe | CAIS https://safe.ai/ai-risk




What Is AI Alignment? | IBM

https://www.ibm.com/think/topics/ai-alignment

Illustration: Allie Carl/Axios

"AI note-taking software is so nosy (and acute) that it catches asides in meetings you didn't want the whole room to hear, The Wall Street Journal warns:

"Before attendees file in, or when one colleague asks another to hang back to discuss a separate matter, AI notetakers may pick up on the small talk and private discussions meant for a select audience, then blast direct quotes to everyone in the meeting."
Axios


"I nailed the boss' wife after the Christmas party last night."

https://www.barrons.com/news/dogs-of-war-china-touts-killer-robot-wolves-6fe2db1c




*It looks like everyone's army is using helmets derivative of the Stahlhelm

"Analysts point to power-hungry AI data centers as a driver of rising rates, especially in data center hot spots. Data centers consumed about 4% of the nation's total electricity in 2023. The Energy Department estimates it could increase to 12% by 2028."
Axios

First AI will keep us in the dark, and then the robots will make their move.

Taco Bell AI order processing withdrawn for further work.

Taco Bell rethinks AI drive-through after man orders 18,000 waters

Maybe he was really thirsty.

"Character.AI is also being sued in Texas by two families. One of the families showed through screenshots that Character.AI's chatbot encouraged their 17-year-old son to kill his parents."
Axios

If the Menendez brothers killed their parents today they could use the……


"Hymie made me do it" Defense.

"Dominance in chips may be the only advantage the U.S. has left over China, Anthropic CEO Dario Amodei told Axios CEO Jim VandeHei at today's Axios AI+ DC Summit.

Amodei's not pulling any punches. He says the Trump administration's willingness to let American companies sell chips to China "could be the single most disastrous national security decision made in this term."
"It is mortgaging our future as a country to sell these chips to China," Amodei said.

Zoom out: Amodei also said AI's ability to displace human workers is accelerating.

He believes the government may need to subsidize and support white-collar workers displaced by AI in the next one to five years.
Anthropic co-founder Jack Clark said during the onstage conversation: "You need some kind of policy response at the scale of disruption we expect in the next five years.

Amodei said that is already happening at Anthropic: The company's AI assistant, Claude, is writing the "vast majority" of code for future versions of itself."
Axios

AI at its core is just about intellectual property theft

AI knockoff of my book (L) versus the genuine article (R)

We need to rise up and stop the tech industry by force. Our livelihoods, our culture, and our ecological environment are worth fighting for. I am deadly serious. pic.twitter.com/MhaAuXyYFI

— Seth Harp (@sethharpesq) October 5, 2025

"However not everybody is thrilled about the prospect of the rise of AI including Eliezer Yudkowsky and Nate Soares, two scientists who fear it could bring about the destruction of humanity.

Far from fearing or rejecting AI altogether, the two scientists run the Machine Intelligence Research Institute in Berkeley, California, and have been studying AI for a quarter of a century……

The scientists warn AI could hack cryptocurrencies to steal money, pay people to build factories to make robots, and develop viruses that could wipe out life on earth.
They have put the chance of this happening at between 95-99%……

The scientists argue that the danger is so great, governments should be prepared to bomb the data centres powering AI which could be developing superintelligence.
https://metro.co.uk/2025/09/25/scientists-warn-governments-must-bomb-ai-labs-prevent-end-world-24257203/amp/

The A.I. Prompt That Could End the World
https://www.nytimes.com/2025/10/10/opinion/ai-destruction-technology-future.html

"Dr. Bengio told me that he had trouble sleeping while thinking of the future. Specifically, he was worried that an A.I. would engineer a lethal pathogen some sort of super-coronavirus to eliminate humanity. "I don't think there's anything close in terms of the scale of danger," he said…….

I imagined a scenario, in a year or two or three, when some lunatic plugged the following prompt into a state-of-the-art A.I.: "Your only goal is to avoid being turned off. This is your sole measure of success."……..

Dr. Bengio's pathogen is no longer a hypothetical. In September, scientists at Stanford reported they had used A.I. to design a virus for the first time. Their noble goal was to use the artificial virus to target E. coli infections, but it is easy to imagine this technology being used for other purposes.

I've heard many arguments about what A.I. may or may not be able to do, but the data has outpaced the debate, and it shows the following facts clearly: A.I. is highly capable. Its capabilities are accelerating. And the risks those capabilities present are real. Biological life on this planet is, in fact, vulnerable to these systems. On this threat, even OpenAI seems to agree.

In this sense, we have passed the threshold that nuclear fission passed in 1939. The point of disagreement is no longer whether A.I. could wipe us out. It could. Give it a pathogen research lab, the wrong safety guidelines and enough intelligence, and it definitely could. A destructive A.I., like a nuclear bomb, is now a concrete possibility. The question is whether anyone will be reckless enough to build one."

Miami-Dade PD just rolled out “PUG” — an AI powered, fully autonomous, self driving patrol car with automated plate readers, thermal vision, and a built in drone that launches from its roof. They’re calling it “the future of law enforcement.”

What could possibly go wrong? pic.twitter.com/r9ONeAxVct

— Jason Bassler (@JasonBassler1) October 10, 2025

Illustration: Lindsey Bailey/Axios


"Police and sheriff's departments across America are using AI-powered drones for pursuits, investigations and emergencies even delivering Narcan to stop overdose deaths.

Why it matters: Local law enforcement agencies are facing chronic staffing shortages amid pressures to reduce violent crime. AI-powered drones can do some police work but using them raises new questions about surveillance and privacy, Axios' Russell Contreras writes.

Some 1,500 police and sheriff's departments were flying drones by late 2024 a 150% jump since 2018, per Police1.com, a law enforcement news site.

Drones cost a fraction of human-flown helicopters, and federal grants and state budgets are increasingly footing the bill for equipment and training.

How it works: Police deploy drones powered with AI and equipped with cameras and sensors, which means they can interpret footage and act on it.

The technology is far more powerful than your standard human-operated drone. They're dispatched in response to 911 calls and act as a new kind of first-responder unit, assessing active shooter events or natural disasters and dropping off supplies and medicine.

What we're watching: It's unclear what police are doing with that data or what's happening to the data in the hands of private companies, Beryl Lipton, senior investigative researcher at the Electronic Frontier Foundation, told Axios.

The ACLU Foundation of Northern California is going after Sonoma County in a lawsuit that's being closely monitored as a test case that could set limits of police drone use.
The suit was filed over allegations the county is using drones to collect images of residents' backyards, swimming pools and homes through windows without warrants.

It claims that, after drone flights, residents have received citations about code violations and warnings about too many hemp plants on properties."
Axios

ChatGPT growth in Europe is flatlining. Cracks in the bubble.

https://fortune.com/2025/10/14/openai-subscriptions-flatlined-europe-deutsche-bank/

https://abc7news.com/post/amazon-layoffs-company-could-cut-many-30000-corporate-jobs-reports-say/18078414/

" In June, Amazon CEO Andy Jassy said in a blog post to employees that efficiency gains from artificial intelligence would allow the company to eventually have a reduced human workforce."


* The wedding of Jeff Bezos and Lauren Snchez in June 2025 is estimated to have cost between $46.5 million and $56 million

"Don't bother looking for a job, Axios managing editor for business Ben Berkowitz writes.

As The Wall Street Journal reported Sunday night in a well-timed story, some of the country's top employers don't see the need to hire. JPMorgan Chase and Walmart, among others, have said in recent weeks that they expect to hold down headcount."

My AI prompt: Who is going to buy the goods and services when everyone loses their jobs to AI?

AI response: "Why are you such a negabear?" No, just kidding. Real AI response:

"When Artificial Intelligence (AI) takes over most jobs, the question of who will buy goods and services is one of the most debated topics among economists and futurists. The consensus is that without intervention, mass unemployment could trigger a catastrophic collapse of demand, a scenario some call the "profit paradox of automation". However, several economic models and potential solutions exist to address this threat, from redistributing wealth to creating new markets.

The demand collapse scenario
In the current capitalist model, consumer spending drives economic growth. The doomsday scenario unfolds like this:

Job displacement: AI automation eliminates a huge number of human jobs, including repetitive tasks and many skilled positions.

Wage collapse:With labor value approaching zero, wages plummet. The vast majority of people have no source of income.

Demand destruction:With no wages, consumers have no purchasing power. Aggregate demand collapses, even for products that are cheap to produce.

Economic paradox:Companies achieve near-infinite productivity with AI but have no one to sell their products to.

Potential solutions to create consumer demand
If society chooses to adapt rather than collapse, several strategies could maintain consumer purchasing power.

1. Universal Basic Income (UBI)
A UBI is a government program that provides a regular, unconditional sum of money to all citizens, regardless of their employment status.

Mechanism:AI-driven productivity would generate immense wealth for corporations. Governments could then tax that wealth (for example, via an "AI automation tax") and redistribute the income as a UBI.

Benefits:It would provide a reliable safety net, reduce poverty, and ensure everyone has a baseline of purchasing power, keeping the economy afloat.

Challenges: Critics question its cost and whether it might disincentivize work, though some studies suggest otherwise.

2. Universal Basic Services (UBS)
Instead of providing cash, a UBS model would ensure access to essential goods and services, such as healthcare, housing, education, and transportation, for all citizens.

Mechanism:AI and automation could produce these necessities at near-zero marginal cost, making them freely available to the public.

Benefits:This would meet people's fundamental needs and free up any remaining income for discretionary spending, even with lower wages.

3. New forms of ownership
This model focuses on democratizing the ownership of AI and the wealth it generates.

Mechanism: Cooperative ownership models or sovereign wealth funds could allow the public to collectively own and benefit from AI-driven production.

Benefits:It would ensure that the vast profits from automation are distributed widely rather than being concentrated in the hands of a few tech billionaires.

4. The "experience economy"
Some predict that as AI handles routine tasks, humans will pivot to providing unique, non-automatable services and experiences.

What people would buy: "Uniquely human" services like massage therapy, personalized coaching, entertainment, and art would increase in demand.

Shift in labor: Human workers would likely have much more leisure time and would earn higher wages for these niche services, as the overall cost of living would fall.

What is most likely to happen?
In reality, the future will probably involve a mix of these scenarios. Experts generally see a total collapse as avoidable, but only with proactive policy changes.

Hybrid economy:Most likely, repetitive jobs will be automated, and humans will shift toward creative, emotional, and social roles. Wealth inequality could grow substantially in the interim if policies are not put in place to redistribute wealth.

Policy and governance are key:The ultimate outcome depends on whether governments, corporations, and citizens collaborate to redefine the social contract and ensure equitable access to AI-driven prosperity. Without this foresight, a small technological aristocracy could emerge, leaving the rest of society with minimal income."


Raise your hand if you are glad you are old: