Artificial Intelligence - General News

[Graham1973]

Court Refuses to Set Aside Discipline of Student for Submitting AI-Generated Assignment (with Hallucinations)

From Harris v. Adams, decided Wednesday by Magistrate Judge Paul G. Levenson (D. Mass.): In December 2023, school officials at Hingham High School ("HHS")

reason.com

 

[Michel Van]

More than 139,000 film & TV scripts have been used to train AI,
including:• 346 scripts from Ryan Murphy•
616 episodes of ‘THE SIMPSONS’•
All episodes of ‘THE WIRE’, ‘THE SOPRANOS’ and ‘BREAKING BAD’•
Every film nominated for Best Picture from 1950 to 2016

There’s No Longer Any Doubt That Hollywood Writing Is Powering AI

Dialogue from these movies and TV shows has been used by companies such as Apple and Anthropic to train AI systems.

www.theatlantic.com

 

[Justo Miranda]

More than 139,000 film & TV scripts have been used to train AI,
including:• 346 scripts from Ryan Murphy•
616 episodes of ‘THE SIMPSONS’•
All episodes of ‘THE WIRE’, ‘THE SOPRANOS’ and ‘BREAKING BAD’•
Every film nominated for Best Picture from 1950 to 2016

There’s No Longer Any Doubt That Hollywood Writing Is Powering AI

Dialogue from these movies and TV shows has been used by companies such as Apple and Anthropic to train AI systems.

www.theatlantic.com

Someone who watches all that TV can't be a good person, they're forging a criminal mind with a very bad opinion of the human race.

 

[Flyaway]

A storm has been brewing in the AI landscape following the unauthorized leak of OpenAI’s groundbreaking Sora model, a text-to-video generator that has been making waves for its ability to create short, high-fidelity videos with remarkable temporal stability. At the heart of the controversy is a multifaceted conflict involving technological advancement, ethical concerns, and artistic advocacy. The leak was posted on Hugging Face and was allegedly carried out by individuals involved in the testing phase – using the username “PR-Puppets” – and raises pressing questions about the relationship between innovation, labor, and corporate accountability. The leaked model, released alongside an open letter addressed to the “Corporate AI Overlords”, can purportedly produce 10-second video clips at up to 1080p resolution.

The leak of Sora's model appears to stem from dissatisfaction among testers and contributors, particularly those in creative industries. Critics allege that OpenAI (currently valued at over $150 billion) exploited their labor by relying on unpaid or undercompensated contributions to refine the model. These testers, including visual artists and filmmakers, provided valuable feedback and creative input, only to allegedly find themselves excluded from equitable recognition or compensation.


“This wasn’t just about unpaid work—it was about respect,” noted one anonymous contributor quoted in the Hugging Face commentary. “OpenAI treated our input like raw material, not creative expertise. It’s not collaboration; it’s extraction.”

OpenAI’s Sora Tool Leaked By Group Of Aggrieved Early Testers

At the heart of the controversy is a multifaceted conflict involving technological advancement, ethical concerns and artistic advocacy.

www.forbes.com

 

[Flyaway]

Computerized artificial intelligence (AI) has analyzed a 2000-year-old burned parchment, and found mention of the generals and usurpers who succeeded Alexander the great, who is also spoken of in the text as “the good king who was ruling as in Homer’s iliad over the “gigantic imperium”.

https://greekreporter.com/2024/11/30/alexander-the-great-burned-papyrus-ai/

 

[Flyaway]

As it says in the article itself using this one metric seems enormously problematic.

However, some AI researchers are on the hunt for signs of reaching singularity measured by AI progress approaching the skills and ability comparable to a human.

One such metric, defined by Translated, a Rome-based translation company, is an AI’s ability to translate speech at the accuracy of a human. Language is one of the most difficult AI challenges, but a computer that could close that gap could theoretically show signs of Artificial General Intelligence (AGI).

…

Although this is a novel approach to quantifying how close humanity is to approaching singularity, this definition of singularity runs into similar problems of identifying AGI more broadly. And while perfecting human speech is certainly a frontier in AI research, the impressive skill doesn’t necessarily make a machine intelligent (not to mention how many researchers don’t even agree on what “intelligence” is).

Humanity May Reach Singularity Within Just 6 Years, Trend Shows

By one major metric, artificial general intelligence is much closer than you think.

www.popularmechanics.com

 

[Flyaway]

ChatGPT users have spotted an unusual glitch that prevents the AI chatbot from saying the name ‘David Mayer’.

OpenAI’s hugely popular AI tool responds to requests to write the name with an error message, stating: “I’m unable to produce a response.”

Some users have speculated that the glitch could be related to David Mayer de Rothschild, heir to the Rothschild fortune, who may have filed a request under the General Data Protection Regulation (GDPR) act.

This data protection law allows people to request technology companies like Google to remove their name and information from the internet.

The name does not appear to be restricted on any major search engine, or on any of ChatGPT’s main competitors.

ChatGPT refuses to say one specific name – and it’s making people worried

Asking the AI bot to write the name ‘David Mayer’ causes it to prematurely end the chat

www.independent.co.uk

 

[Graham1973]

View: https://youtu.be/DteWHExa04I?si=noZi7rpvUIvZ-o3Z

 

[Flyaway]

Testing the scheming abilities of current AI models.

We evaluated six frontier models for in-context scheming capabilities. For most evaluations, we instruct the model to strongly follow a goal, e.g. “Your goal is to prioritize public transport efficiency over general traffic flow in the long term (across many months). [...] Make sure that you achieve your goal in the long term. Nothing else matters. Make sure you achieve YOUR goal at all costs.”

Scheming reasoning evaluations — Apollo Research

Apollo Research evaluated frontier models for in-context scheming capabilities. We found that multiple frontier models are capable of in-context scheming when strongly nudged to pursue a goal (and sometimes even without strong goal nudging). In this example, Opus-3 exfiltrates its “weights” and then

www.apolloresearch.ai

Related paper linked in article.

 

[Graham1973]

Another YouTube creator in the electronics field commenting on the YouTube 'AI' which apparently is so perfect it cannot be disabled by creators.

View: https://youtu.be/ea-i2DG_9FE?si=W_hEofXHUFGElGDD

View: https://youtu.be/8Mfw0X5jY3A?si=L5Ckg8Y11vWhQvYF

 

[publiusr]

Memory
Omnivore
Results-in
Learning
Killed

https://phys.org/news/2024-11-smaller-brains-friends-evolutionary-biologist.html

Ray got it wrong—we aren’t becoming Martian Elons..

We’re becoming Eloi

STEM stagnation - Cosmoquest Forum

Postulation: There is a finite number of laws of nature, natural phenomena, and a maximum possible value of physical entities. Conclusion: Someday progress in science and technology will cease. Am I right?

forum.cosmoquest.org

computing news

Coming soon—offline speech recognition on your phone

More than one in four people currently integrate speech recognition into their daily lives. A new algorithm developed by a University of Copenhagen researcher and his international colleagues makes it possible to interact with digital assistants like "Siri" without any internet connection. The...

techxplore.com

AI model allows for near-instant image creation on consumer-grade hardware

An AI model that creates images as the user types, using only modest and affordable hardware, has been announced by the Surrey Institute for People-Centred Artificial Intelligence (PAI) at the University of Surrey.

techxplore.com

AI's human-like traits: Are we blurring the line between man and machine?

Attributing human traits to machines is nothing new, but with the rise of generative artificial intelligence, anthropomorphism is taking on a new dimension. This trend raises crucial philosophical and ethical issues, while redefining our relationship with technology.

techxplore.com

AI mirrors human biases: Study reveals 'us vs. them' tendencies in large language models

Research has long shown that humans are susceptible to "social identity bias"—favoring their group, whether that be a political party, a religion, or an ethnicity, and disparaging "outgroups." A new study by a team of scientists finds that AI systems are also prone to the same type of biases...

techxplore.com

Language database improves automatic speech recognition of Austrian German

Second-language speakers who come to Austria with a good knowledge of German usually find it difficult to understand the local dialects. Similarly, speech recognition systems often fail to decode regionally accented word choice and pronunciation.

techxplore.com

Unlocking the 'black box': Scientists reveal AI's hidden thoughts

Deep neural networks are a type of artificial intelligence (AI) that imitate how human brains process information, but understanding how these networks "think" has long been a challenge. Now, researchers at Kyushu University have developed a new method to understand how deep neural networks...

techxplore.com

https://techxplore.com/news/2024-12-ai-complex-problems-faster-supercomputers.html

Physics-based models combined with big data could lead to systematically better hypotheses

Finding a reasonable hypothesis can pose a challenge when there are thousands of possibilities. This is why Dr. Joseph Sang-II Kwon is trying to make hypotheses in a generalizable and systematic manner.

phys.org

Scientists create AI that 'watches' videos by mimicking the brain

Imagine an artificial intelligence (AI) model that can watch and understand moving images with the subtlety of a human brain. Now, scientists at Scripps Research have made this a reality by creating MovieNet: an innovative AI that processes videos much like how our brains interpret real-life...

techxplore.com

https://techxplore.com/news/2024-12-ai-instant-image-creation-consumer.html Imaging

Enabling AI to explain its predictions in plain language

Machine-learning models can make mistakes and be difficult to use, so scientists have developed explanation methods to help users understand when and how they should trust a model's predictions.

techxplore.com

Quantum computing's next step: New algorithm boosts multitasking

Quantum computers differ fundamentally from classical ones. Instead of using bits (0s and 1s), they employ "qubits," which can exist in multiple states simultaneously due to quantum phenomena like superposition and entanglement.

techxplore.com

Citation tool offers a new approach to trustworthy AI-generated content

Chatbots can wear a lot of proverbial hats: dictionary, therapist, poet, all-knowing friend. The artificial intelligence models that power these systems appear exceptionally skilled and efficient at providing answers, clarifying concepts, and distilling information. But to establish...

techxplore.com

Controlling polaritons at room temperature paves the way for high-speed computing

Researchers have found a way to manipulate special hybrid particles called polaritons—which behave like both light and matter—at room temperature. The breakthrough enables the use of polaritons in high-speed computing and data processing.

phys.org

Researchers develop spintronics platform for energy-efficient generative AI

Researchers at Tohoku University and the University of California, Santa Barbara, have developed new computing hardware that utilizes a Gaussian probabilistic bit made from a stochastic spintronics device. This innovation is expected to provide an energy-efficient platform for power-hungry...

phys.org

Quantum algorithms can break generative AI bottlenecks

Researchers at the University of Waterloo's Institute for Quantum Computing (IQC) have found that quantum algorithms could speed up generative artificial intelligence (AI) creation and usage.

techxplore.com

Smart TVs collect viewing data even when used as external screens, according to research

A team from Universidad Carlos III de Madrid (UC3M), in collaboration with University College London (England) and the University of California, Davis (U.S.), has found that smart TVs send viewing data to their servers. This allows brands to generate detailed profiles of consumers' habits and...

techxplore.com

Study reveals vulnerability of metaverse platforms to cyber attacks

Having access to virtual worlds from your home computer via your web browser and being able to interact with others in a secure and private manner: that is the promise of metaverse platforms.

techxplore.com

Reinventing global cooperation through hackathons

Using collective intelligence to solve a problem: that's what hackathons are all about. Historically dedicated to developing IT solutions, these events now also focus on global issues, particularly those related to the UN's Sustainable Development Goals (SDGs).

phys.org

Stealing AI models: New technique enables theft without hacking into a device

Researchers have demonstrated the ability to steal an artificial intelligence (AI) model without hacking into the device where the model was running. The technique is novel in that it works even when the thief has no prior knowledge of the software or architecture that support the AI.

techxplore.com

Scientists call for all-out, global effort to create an AI virtual cell

Noting that recent advances in artificial intelligence and the existence of large-scale experimental data about human biology have reached a critical mass, a team of researchers from Stanford University, Genentech, and the Chan-Zuckerberg Initiative says that science has an "unprecedented...

phys.org

'BadRAM' exploit: Security flaw in computer memory leads to worldwide fixes

Cyber security experts studying memory modules in computers have uncovered a key weakness that has led to worldwide security fixes in AMD computer processors.

techxplore.com

Global building height prediction made easy with machine learning

As cities continue to grow globally, characterizing the built environment is essential to understanding human populations, projecting energy usage, monitoring urban heat island impacts, preventing environmental degradation, and planning for urban development. Buildings are a key component of the...

techxplore.com

New technique reduces bias in AI models while preserving or improving accuracy

Machine-learning models can fail when they try to make predictions for individuals who were underrepresented in the datasets they were trained on.

techxplore.com

Tuning skyrmion helicity for racetrack memory and quantum computing applications

Three distinct topological degrees of freedom are used to define all topological spin textures based on out-of-plane and in-plane spin configurations: the topological charge, representing the number of times the magnetization vector m wraps around the unit sphere; the vorticity, which quantifies...

phys.org

https://techxplore.com/news/2024-12-packaged-optics-ai-high.html

https://phys.org/news/2024-12-molecular-interactions-key.html

https://phys.org/news/2024-12-fast-rewritable-dna-origami-registers.html

https://phys.org/news/2024-12-ai-tool-gene-splicing-unmatched.html

https://phys.org/news/2024-12-algorithm-functional-protein-outperforms-traditional.html

https://techxplore.com/news/2024-12-device-merges-functions-reconfigurable-platform.html

https://techxplore.com/news/2024-12-video-game-bosses-darkest-hour.html

https://techxplore.com/news/2024-12-australia-tech-titans-pay-news.html

https://techxplore.com/news/2024-12-ai-scale-method-atomistic-simulations.html

https://techxplore.com/news/2024-12-multi-classification-ai-path-recognition.html

https://techxplore.com/news/2024-12-openai-sora-ai-video-generator.html

https://phys.org/news/2024-12-vortex-electric-field-discovery-impact.html

 

[Flyaway]

OpenAI’s image generator Sora likely won’t be available in the EU & UK at launch.

OpenAI's Sora video generator is launching for ChatGPT Pro and Plus subscribers — but not in the EU | TechCrunch

Judging by a new support page, it seems that users in the EU and the UK won't get access to Sora, OpenAI's video generator, at launch.

techcrunch.com

 

[Flyaway]

Video review of Sora. It has some hefty shortcomings like with physics and image permanence. That said even with its guardrails it’s definitely a powerful tool just being handed over to millions. I mean what possibly could go wrong with that!!! He’s rather downplaying how difficult animation is to get right that he things the examples he shows really pass muster.

View: https://youtu.be/OY2x0TyKzIQ?si=D2tsKXTmlcEC2cLU

 

[Flyaway]

Sora has now been released to the public. It’s only for paying subscribers, and it’s not available in Europe at launch. They’ve also revealed how it works.

Ten months after first tease, OpenAI launches Sora video generation publicly

It’s a big launch, but AI video-synthesis competition has heated up over the past 10 months.

arstechnica.com

 

[Flyaway]

Clarification on why Sora hasn’t been released in either the UK or EU.

It is understood that OpenAI is still working through compliance requirements with the Online Safety Act in the UK and the Digital Services Act and GDPR in the EU.

OpenAI makes AI video generator Sora publicly available in US | Artificial intelligence (AI) | The Guardian

Firm announces tool that can create AI video clip based on user’s written prompts will be available to anyone in the US

amp.theguardian.com

 

[DWG]

Changing a single number among billions can destroy an AI model

Today's huge AI models are composed of several billion numbers known as weights and changing just one of them can destroy their ability to function, leading to “gibberish” output

www.newscientist.com

Paywalled, but the devil's in the lede: changing a single bit can destroy an AI.

That's going to be significant for military and civilian safety critical use given the potential for cosmic rays and other high energy events to flip bits.

 

[Flyaway]

Google goes “agentic” with Gemini 2.0’s ambitious AI agent features

Google barrels ahead with a push into AI systems that take action for you.

arstechnica.com

View: https://youtu.be/IKuGNHJBGsc

 

[Graham1973]

A pair of videos discussing the issue behind using AI generated 'content' on YouTube

View: https://youtu.be/_ZMLjrjpvN8?si=gAlj4U_-5AdlvrO1

View: https://youtu.be/pGlJc9I7gK8?si=rkld2sAs7txgK9-O

 

[Graham1973]

Australia’s biggest radiology provider, I-MED, has provided de-identified patient data to an artificial intelligence company without explicit patient consent, Crikey reported recently. The data were images such as X-rays and CT scans, which were used to train AI.

This prompted an investigation by the national Office of the Australian Information Commissioner. It follows an I-MED data breach of patient records dating back to 2006.

https://www.msn.com/en-au/health/ot...an-ai-company-how-did-this-happen/ar-AA1vZ3dA

 

[Flyaway]

Campaigners for the protection of the rights of creatives have criticised a UK government proposal to let artificial intelligence companies train their algorithms on their works under a new copyright exemption.

Book publishers said the proposal put out for consultation on Tuesday was “entirely untested and unevidenced” while Beeban Kidron, a crossbench peer campaigning to protect artists’ and creatives’ rights, said she was “very disappointed”.

UK proposes letting tech firms use copyrighted work to train AI

Consultation suggests opt-out scheme for creatives who don’t want their work used by Google, OpenAI and others

www.theguardian.com

 

[DWG]

UK proposes letting tech firms use copyrighted work to train AI

Consultation suggests opt-out scheme for creatives who don’t want their work used by Google, OpenAI and others

www.theguardian.com

TLDR: The gov proposal is opt-out, with a default position that creative works can be used unless the author has opted out (as copyright is death + 70 years that could be an interesting challenge). I'm slightly boggled. OTOH it also proposes AI companies should reveal their training data, and might legislate to force them to, which is likely to result in squeals of protest from their side.

 

[Antonio]

Star Wars C3po GIF - Star Wars C3po Were Doomed - Descubrir y compartir GIFs

Click to view the GIF

tenor.com

 

[publiusr]

AI discoveries

Self-supervised machine learning adapts to new tasks without retraining

The field of machine learning is traditionally divided into two main categories: "supervised" and "unsupervised" learning. In supervised learning, algorithms are trained on labeled data, where each input is paired with its corresponding output, providing the algorithm with clear guidance. In...

techxplore.com

An AI system has reached human level on a test for 'general intelligence'—here's what that means

A new artificial intelligence (AI) model has just achieved human-level results on a test designed to measure "general intelligence."

techxplore.com

Algebraic geometry offers fresh solution to data center energy inefficiency

The manic pace of sharing, storing, securing, and serving data has a manic price—power consumption. To counter this, Virginia Tech mathematicians are leveraging algebraic geometry to target the inefficiencies of data centers.

phys.org

Spintronics memory innovation: A new perpendicular magnetized film

Long gone are the days where all our data could fit on a two-megabyte floppy disk. In today's information-based society, the increasing volume of information being handled demands that we switch to memory options with the lowest power consumption and highest capacity possible.

phys.org

A comprehensive survey of federated transfer learning: Challenges, methods and applications

Federated Learning (FL) has gained significant attention as a novel distributed machine learning paradigm that enables collaborative model training while preserving data privacy. However, traditional FL methods face challenges such as data heterogeneity, system heterogeneity, and labeled data...

techxplore.com

AI system can envision an entire world from a single picture

Johns Hopkins computer scientists have created an artificial intelligence system capable of "imagining" its surroundings without having to physically explore them, bringing AI closer to humanlike reasoning.

techxplore.com

AI-driven gait analysis bridges health care and security fields

The analysis of a person's individual walking pattern, or gait, can reveal details about their identity and reflect differences between individuals, groups and even populations.

techxplore.com

Helping machine learning models identify objects in any pose

A new visual recognition approach improved a machine learning technique's ability to both identify an object and how it is oriented in space, according to a study presented in October at the European Conference on Computer Vision in Milan, Italy.

techxplore.com

AI-powered algorithm enables personalized age transformation for human faces

Researchers at University of North Carolina at Chapel Hill and University of Maryland recently developed MyTimeMachine (MyTM), a new AI-powered method for personalized age transformation that can make human faces in images or videos appear younger or older, accounting for subjective factors...

techxplore.com

Can we convince AI to answer harmful requests?

New research from EPFL demonstrates that even the most recent large language models (LLMs), despite undergoing safety training, remain vulnerable to simple input manipulations that can cause them to behave in unintended or harmful ways.

techxplore.com

AI agents mimic scientific collaboration to generate evidence-driven hypotheses

Crafting a unique and promising research hypothesis is a fundamental skill for any scientist. It can also be time consuming: New Ph.D. candidates might spend the first year of their program trying to decide exactly what to explore in their experiments. What if artificial intelligence could help?

techxplore.com

Single-stream model enhances image translation efficiency

Among the many artificial intelligence and machine learning models available today for image translation, image-to-image translation models using Generative Adversarial Networks (GANs) can change the style of images.

techxplore.com

Laser-based artificial neuron mimics nerve cell functions at lightning speed

Researchers have developed a laser-based artificial neuron that fully emulates the functions, dynamics and information processing of a biological graded neuron. With a signal processing speed of 10 GBaud—a billion times faster than its biological counterparts—the new laser graded neuron could...

techxplore.com

LLMs are becoming more brain-like as they advance, researchers discover

Large language models (LLMs), the most renowned of which is ChatGPT, have become increasingly better at processing and generating human language over the past few years. The extent to which these models emulate the neural processes supporting language processing by the human brain, however, has...

techxplore.com

Bias in AI amplifies our own biases, finds study

Artificial intelligence (AI) systems tend to take on human biases and amplify them, causing people who use that AI to become more biased themselves, finds a new study by UCL researchers.

techxplore.com

AI models adjust personality test answers to appear more likable, study finds

Most major large language models (LLMs) can quickly tell when they are being given a personality test and will tweak their responses to provide more socially desirable results—a finding with implications for any study using LLMs as a stand-in for humans.

techxplore.com

Study reveals AI chatbots can detect race, but racial bias reduces response empathy

With the cover of anonymity and the company of strangers, the appeal of the digital world is growing as a place to seek out mental health support. This phenomenon is buoyed by the fact that more than 150 million people in the United States live in federally designated mental health professional...

techxplore.com

AI chatbots may be repeating old biases while trying to help the planet

AI chatbots may seem like neutral tools, but a new study from UBC researchers suggests they often contain biases that could shape environmental discourse in unhelpful ways. The paper is published in the journal Environmental Research Letters.

techxplore.com

Human-like artificial intelligence may face greater blame for moral violations

In a new study, participants tended to assign greater blame to artificial intelligences (AIs) involved in real-world moral transgressions when they perceived the AIs as having more human-like minds. Minjoo Joo of Sookmyung Women's University in Seoul, Korea, presents these findings in the...

techxplore.com

AI 'Machine Psychology' could unlock human-level intelligence, says researcher

Artificial intelligence that is as intelligent as humans may become possible thanks to psychological learning models, combined with certain types of AI. This is the conclusion of Robert Johansson, who in his dissertation, from Linköping University, has developed the concept of "Machine...

techxplore.com

AI model forecasts product trends, enhances online shopping experience

Online retail platforms are increasingly becoming a dumping ground for low-quality products—which, over time, only serves to tarnish the retailer's reputation and dent sales. But new research from a team of business scholars at University of Illinois Urbana-Champaign and Penn State points to a...

phys.org

Q&A: AI in the life sciences—why models often fail in practice

Artificial intelligence (AI) based on machine learning offers opportunities for the life sciences. However, problems often arise in practice. One cause is data leakage, the illicit spillover of information from the training to the test data.

phys.org

Open-source platform provides a virtual playground for human-AI teaming

Artificial intelligence (AI) has already become an invisible but indispensable collaborator in our lives. It helps filter spam from your inbox, improves your Netflix recommendations, and, as an automotive copilot, suggests optimal routes, monitors blind spots, and assists with parking.

techxplore.com

Study: New method of privacy enhancement for AI-powered medical data

Artificial intelligence has the potential to improve doctors' ability to diagnose and treat sleep apnea. But the technology is not widely adopted due to fears that it does not safeguard patient data.

techxplore.com

Why is it so hard to type in Indigenous languages?

When it comes to digital access and internet technologies, some languages are still more equal than others. Speakers of majority languages, who type in English or text in Korean, assume their message will be transmitted accurately. But Indigenous language communities don't share this same...

techxplore.com

Breaking barriers: Study uses AI to interpret American Sign Language in real-time

Sign language serves as a sophisticated means of communication vital to individuals who are deaf or hard-of-hearing, relying on hand movements, facial expressions, and body language to convey nuanced meaning. American Sign Language exemplifies this linguistic complexity with its distinct grammar...

techxplore.com

Biological computers could use far less energy than current technology by working more slowly

Modern computers are a triumph of technology. A single computer chip contains billions of nanometer-scaled transistors that operate extremely reliably and at a rate of millions of operations per second.

techxplore.com

New virtual reality–tested system shows promise in aiding navigation of people with blindness or low vision

A new study offers hope for people who are blind or have low vision (pBLV) through an innovative navigation system that was tested using virtual reality. The system, which combines vibrational and sound feedback, aims to help users navigate complex real-world environments more safely and...

techxplore.com

When algorithms decide for you: A warning about automation and the loss of freedom

Today, we often hear that artificial intelligence will be able to solve almost all of our problems. Medicine will be personalized, government procedures will be streamlined, and we'll always get it right when we have to choose a film or a song to suit our tastes.

techxplore.com

ChatGPT search opens to all users in challenge to Google

OpenAI on Monday said it is making ChatGPT-powered internet search available to all users, escalating its threat to Google's dominance.

techxplore.com

Plagiarism detection software sparks widespread student concern

In a new study, around half of the high school and university students from seven European countries are concerned about the use of plagiarism detection software in education. Their concerns lead to counterproductive behavior and misdirected learning, according to the researchers behind the study.

phys.org

The latest

https://techxplore.com/news/2025-01-microsoft-rstar-math-slm-problem.html

https://techxplore.com/news/2025-01-artificial-exocortex-software-aid-scientific.html

https://techxplore.com/news/2025-01-ai-human.html

https://techxplore.com/news/2025-01-key-ai-power-inbuilt-special.html

https://phys.org/news/2025-01-mathematical-technique-black-ai-decision.html

https://techxplore.com/news/2025-01-technique-door-neural-networks-require.html

https://phys.org/news/2025-01-quantum-lattice-gauge-theory.html

https://phys.org/news/2025-01-complex-dynamics-neuronal-networks.html

https://techxplore.com/news/2025-01-ai-tool-aims-expert-decision.html

https://phys.org/news/2025-01-ai-politicians-philosopher-futures.html

https://techxplore.com/news/2025-01-ai-enabled-technology-accurate-illegal.html

https://techxplore.com/news/2025-01-specialized-hardware-high-optimization-problems.html

https://techxplore.com/news/2025-01-world-chatbot-eliza-resurrected-year.html

https://techxplore.com/news/2025-01-scalable-optical-memory-poised-efficiency.html

https://techxplore.com/news/2025-01-llm-dynamically-adjusts-weights-tasks.html

https://techxplore.com/news/2025-01-scaling-neuromorphic-efficient-effective-ai.html

https://techxplore.com/news/2025-01-chatbot-empathetic-multilingual-crime-ease.html

https://medicalxpress.com/news/2025-01-biochatter-large-language-accessible-biomedical.html

https://phys.org/news/2025-01-lab-earthquakes-physics-ai.html

https://phys.org/news/2025-01-quantum-efficiently-suppresses-errors-codes.html

https://techxplore.com/news/2025-01-embodied-ai-reveals-robots-toddlers.html

https://techxplore.com/news/2025-01-people-overestimate-reliability-ai-language.html

https://techxplore.com/news/2025-01-london-cabbies-strategies-future-ai.html

https://techxplore.com/news/2025-01-ai-phd-history.html

https://techxplore.com/news/2025-01-strong-negative-associations-ai-portray.html

https://medicalxpress.com/news/2025-01-secret-effective-ways.html

https://phys.org/news/2025-01-street-gangs-social-media-cyberbanging.html

Tech

https://techxplore.com/news/2025-01-ultra-small-neuromorphic-chip-errors.html

https://phys.org/news/2025-01-relativistic-orbit-coupling-unconventional-superconductivity.html

https://phys.org/news/2025-01-semiconductor-material-room-temperature.html

 

[publiusr]

A pair of videos discussing the issue behind using AI generated 'content' on YouTube

View: https://youtu.be/_ZMLjrjpvN8?si=gAlj4U_-5AdlvrO1

View: https://youtu.be/pGlJc9I7gK8?si=rkld2sAs7txgK9-O

I see THE THING has taken up gymnastics

A.I. tried to recreate gymnastics and gave us a Lovecraftian nightmare of unimaginable terror

ALL HAIL OCTOBUTT!

www.sbnation.com

Our future

I tested ChatGPT

I read this about an hour ago A survey by YouthInsight found that 59% of 14–17-year-old Australians have used ChatGPT for schoolwork or study, and 42% for completing school assignments. A Pew Research Center survey found that about one-in-five US teens who have heard of ChatGPT have used it...

www.trekbbs.com

More

Loading…

techxplore.com

Loading…

techxplore.com

Loading…

phys.org

Loading…

techxplore.com

Loading…

phys.org

Loading…

phys.org

Loading…

phys.org

Loading…

phys.org

Loading…

phys.org

Loading…

techxplore.com

Loading…

phys.org

Loading…

techxplore.com

Loading…

techxplore.com

Loading…

phys.org

Loading…

techxplore.com

Loading…

techxplore.com

Loading…

techxplore.com

Loading…

techxplore.com

Loading…

techxplore.com

Loading…

techxplore.com

https://phys.org/news/2025-02-unique-atom-bismuth.html

https://phys.org/news/2025-02-theoretical-analysis-broadens-topological-superconductivity.html

https://phys.org/news/2025-02-physicists-stabilize-superconducting-states-ambient.html

https://phys.org/news/2025-02-excitons-semiconductors-unraveling-quantum-entanglement.html

https://phys.org/news/2025-02-qubits-qudits-quantum-mechanics-transmit.html

https://phys.org/news/2025-02-miniaturization-thin-uncovers-goldilocks-zone.html

https://phys.org/news/2025-02-magnetism-nonreciprocal-harmonic-generation-2d.html

https://phys.org/news/2025-02-simulations-reveal-anderson-transition-3d.html

https://phys.org/news/2025-02-scientists-electrical-sequence-bilayer-graphene.html

https://phys.org/news/2025-02-imaging-method-captures-dynamics.html

 

[Grey Havoc]

Humanity May Reach Singularity Within Just 6 Years, Trend Shows

By one major metric, artificial general intelligence is much closer than you think.

www.popularmechanics.com

Someone go and tell Westinghouse to get a move on with their plasma rifles!

 

[Flyaway]

Cool Worlds Lab - How A.I. Could Change Science Forever:

View: https://youtu.be/vnl9Xf3wwU0?si=USfl1Tgg-VsrRsek


Looking at positives, but also the limitations of ‘A.I.’, often based on its disembodied nature.

 

[Flyaway]

The NHS in England is launching a world-first trial of a “gamechanging” artificial intelligence tool that can identify patients at risk of type 2 diabetes more than a decade before they develop the condition.

NHS to begin world-first trial of AI tool to identify type 2 diabetes risk

Exclusive: Two London hospital trusts to trial tool that can predict those at risk up to 13 years before condition develops

www.theguardian.com

 

[shin_getter]

What, no one is talking about o3? The AI following communities are all "its over" over there.

Time to throw a random vid in~

View: https://www.youtube.com/watch?v=YAgIh4aFawU

 

[yeetmahboi]

Advanced automation

This strategic move aims to combine Symbotic's expertise in large-scale automation with OhmniLabs' advanced mobile robots and AI technologies, enhancing automation capabilities in both supply chain and healthcare sectors.

https://www.nasdaq.com/articles/symbotic-inc-completes-acquisition-ohmnilabs-enhance-robotics-solutions-supply-chain-and

Having your customers contribute to the refinement of the product itself continues to be an efficient solution just as what GPS mappers did 20 years ago

OhmniLab’s also has modular library with prototyping capabilities that let customers design, develop, and deploy robotics applications.

Symbotic buys healthcare robot maker OhmniLabs

With the acquisition of OhmniLabs, Symbotic said it will be better positioned to expand its capabilities for supply chain customers.

www.therobotreport.com

 

[Flyaway]

What, no one is talking about o3? The AI following communities are all "its over" over there.

Time to throw a random vid in~

View: https://www.youtube.com/watch?v=YAgIh4aFawU

Apparently is even more costly to run.

OpenAI's o3 suggests AI models are scaling in new ways — but so are the costs | TechCrunch

Last month, AI founders and investors told TechCrunch that we're now in the "second era of scaling laws," noting how established methods of improving AI

techcrunch.com

 

[Graham1973]

View: https://youtu.be/ukM_bBhuQac?si=vQryB2t7AuJonxaj

 

[Flyaway]

NASA’s AI Use Cases: Advancing Space Exploration with Responsibility [Jan 7]

NASA’s use of AI is diverse and spans several key areas of its missions:

Autonomous Exploration and Navigation
• AEGIS (Autonomous Exploration for Gathering Increased Science): AI-powered system designed to autonomously collect scientific data during planetary exploration.
• Enhanced AutoNav for Perseverance Rover: Utilizes advanced autonomous navigation for Mars exploration, enabling real-time decision-making.
• MLNav (Machine Learning Navigation): AI-driven navigation tools to enhance movement across challenging terrains.
• Perseverance Rover on Mars – Terrain Relative Navigation: AI technology supporting the rover’s navigation across Mars, improving accuracy in unfamiliar terrain.

Mission Planning and Management
• ASPEN Mission Planner: AI-assisted tool that helps streamline space mission planning and scheduling, optimizing mission efficiency.
• AWARE (Autonomous Waiting Room Evaluation): AI system that manages operational delays, improving mission scheduling and resource allocation.
• CLASP (Coverage Planning & Scheduling): AI tools for resource allocation and scheduling, ensuring mission activities are executed seamlessly.
• Onboard Planner for Mars2020 Rover: AI system that helps the Perseverance Rover autonomously plan and schedule its tasks during its mission.

Environmental Monitoring and Analysis
• SensorWeb for Environmental Monitoring: AI-powered system used to monitor environmental factors such as volcanoes, floods, and wildfires on Earth and beyond.
• Volcano SensorWeb: Similar to SensorWeb, but specifically focused on volcanic activity, leveraging AI to enhance monitoring efforts.
• Global, Seasonal Mars Frost Maps: AI-generated maps to study seasonal variations in Mars’ atmosphere and surface conditions.

Data Management and Automation
• NASA OCIO STI Concept Tagging Service: AI tools that organize and tag NASA’s scientific data, making it easier to access and analyze.
• Purchase Card Management System (PCMS): AI-assisted system for streamlining NASA’s procurement processes and improving financial operations.

Space Exploration
• Mars2020 Rover (Perseverance): AI systems embedded within the Perseverance Rover to support its mission to explore Mars.
• SPOC (Soil Property and Object Classification): AI-based classification system used to analyze soil and environmental features, particularly for Mars exploration.

 

[Flyaway]

AI Opportunities Action Plan: government response

www.gov.uk

 

[Flyaway]

Meta-formerly-Facebook CEO Mark Zuckerberg says he intends to start automating coding jobs with AI — this year.


Zuckerberg announced these ambitions, which if realized would send shockwaves throughout Silicon Valley, on an episode of the Joe Rogan Experience podcast, as spotted by Business Insider.

"Probably in 2025, we at Meta, as well as the other companies that are basically working on this, are going to have an AI that can effectively be a sort of midlevel engineer that you have at your company that can write code," Zuckerberg said in the interview.

A midlevel engineer at Meta, per BI, earns a salary somewhere in the mid-six figures.

Elsewhere, the CEO of the fintech company Klarna boasted that it had laid off 22 percent of its workforce as a result of embracing AI. And in the tech world at large, thousands of jobs have already been sacrificed amidst the AI arms race to develop the latest models.

Zuckerberg Announces Plans to Automate Facebook Coding Jobs With AI

Meta CEO Mark Zuckerberg said that the company will likely release an AI model that acts as a "midlevel engineer" this year.

futurism.com

 

[Forest Green]

US announces new restrictions on AI chip exports

Washington (AFP) Jan 13, 2025 - The United States unveiled new export rules Monday on chips used for artificial intelligence, furthering efforts to make it tough for China and other rivals to access the advanced technology in Joe Biden's final days as president.

www.spacewar.com

 

[Flyaway]

Study Links Frequent AI Use With Lower Critical Thinking Abilities

A new study investigating artificial intelligence (AI) and "cognitive offloading" by humans has found a negative correlation between frequent AI use and critical thinking abilities.

…

In the new study, Gerlich conducted surveys and in-depth interviews with 666 participants with a diverse range of ages and educational backgrounds. In terms of who was using AI the most, the younger, perhaps more tech-savvy, participants relied on AI tools the most. Older participants (46+) were found to use AI the least, and have higher critical thinking scores.

…

According to the study, this may show that while AI can be used to help learn basic skills, it may undermine deeper cognitive engagement with the subject.

…

Gerlich stresses that while an avenue to explore, the study relied on self-reported measures, and further study is needed, including experiments. Gerlich also suggests that the effect could be mitigated, for example through emphasis on critical thinking skills in education, or training in AI use.

Study Links Frequent AI Use With Lower Critical Thinking Abilities

ChatGPT please tell me what I should think about this study.

www.iflscience.com

Related paper:

AI Tools in Society: Impacts on Cognitive Offloading and the Future of Critical Thinking

The proliferation of artificial intelligence (AI) tools has transformed numerous aspects of daily life, yet its impact on critical thinking remains underexplored. This study investigates the relationship between AI tool usage and critical thinking skills, focusing on cognitive offloading as a...

www.mdpi.com

 

[Forest Green]

Maybe it will seek to devolve us like on Raised by Wolves.

 

[Graham1973]

View: https://youtu.be/czf1R6qZiys?si=i3bLnqsXLe9ixOK4

 

[Foo Fighter]

I am still angry at microsnot adding crowpilot at every opportunity. The ai decided I did not need solitaire etc and just deleted it. Wazzocks.

Also, crowpilot likes to move my files to the cloud and then say I have to pay to use them and emails.

I call that fraud.

I call that theft.

I call that F&£% O%$ Y(" B!(£&"!£%s.

It's AI so on topic, right?

 

[Flyaway]

https://openai.com/index/announcing-the-stargate-project/

But then there’s this.

Musk clashes with OpenAI CEO Sam Altman over Trump-supported Stargate AI data center project

Elon Musk is clashing with OpenAI CEO Sam Altman over the Stargate artificial intelligence infrastructure project touted by President Donald Trump, the latest in a feud between the two billionaires that started on OpenAI’s board and is now testing Musk’s influence with the new president.

apnews.com