41 place 0

969 Apple Researchers Challenge AI Reasoning Claims With Controlled Puzzle Tests

Slashdot
msmash @ Slashdot · 06/09/2025 10:00 EDT

Apple Researchers Challenge AI Reasoning Claims With Controlled Puzzle Tests

Apple researchers have found that state-of-the-art "reasoning" AI models like OpenAI's o3-mini, Gemini (with thinking mode-enabled), Claude 3.7, DeepSeek-R1 face complete performance collapse [PDF] beyond certain complexity thresholds when tested on controllable puzzle environments. The finding raises questions about the true reasoning capabilities of large language models.

The study, which examined models using Tower of Hanoi, checker jumping, river crossing, and blocks world puzzles rather than standard

To see detailed statistics for the news please log in »

Read the original

Add your comment
You must be logged in with Facebook to read and write comments.

A newsletter a day!

You may get 10 most important news around midday in daily newsletter. Press the button and we will send you the most important news only, no spam attached.

or register

LIKE us on Facebook so you won't miss the most important news of the day!

News from the same source
Slashdot Slashdot
Business Insider
Katie Notopoulos @ Business Insider 1 place · today 18:25 EDT

I regret seeing that Coldplay 'kiss cam' video

Chris Martin, why does Coldplay have a "kiss cam," anyway? I'm not sure I want to know about what happened between two adults outside Boston. Read more

1,663 fresh

Gizmodo
Ed Cara @ Gizmodo 1 place · today 14:50 EDT

More Signs RFK Jr. Wants to Be Your President in 2028

RFK Jr.'s super PAC could be laying the groundwork for MAHA in the White House, a recent report suggests. Read more

651 fresh

Wired
Leah Feiger, Makena Kelly, Vittoria Elliott, Matt Giles @ Wired 1 place · today 17:44 EDT

ICE Is Getting Unprecedented Access to Medicaid Data

A new agreement viewed by WIRED gives ICE direct access to a federal database containing sensitive medical data on tens of millions of Americans, with the goal of locating immigrants. Read more

629 fresh

Gizmodo
Luc Olinga @ Gizmodo 2 place · today 12:18 EDT

Elon Musk Wants to Turn AI Into a Cosmic Religion

Its survival hinges on spreading consciousness and populating the galaxy, he claims. Read more

569

Slashdot
BeauHD @ Slashdot 1 place · today 20:45 EDT

Ukrainian Hackers Claim To Have Destroyed Major Russian Drone Maker's Entire Network

Ukrainian hacker group BO Team, with help from the Ukrainian Cyber Alliance and possibly Ukraine's military, claims to have wiped out one of Russia's largest military drone manufacturers, destroying 47TB of production data and even disabling the doors in the facility. "Or, as described by the hacking collective (per Google translate), they 'deeply penetrated' the drone manufacturer 'to the very tonsils of demilitarization and denazification,'" reports The Register. From the... Read more

564 fresh

CNET
Macy Meyer @ CNET 1 place · today 19:48 EDT

Get the Powerful Blender I Use Every Day for Almost Half the Retail Price

The Chefman Obliterator is the blender I turn to when I want to make smoothies, pesto and more. And you can get it for under $100. Read more

542 fresh

Business Insider
Madeline Berg,Tim Paradis @ Business Insider 2 place · today 17:22 EDT

The Coldplay 'kiss cam' clip the internet can't stop talking about

A video appearing to show a tech CEO and his head of HR embracing at a Coldplay concert spread around social media at the speed of sound. Read more

450 fresh

MacRumors
Juli Clover @ MacRumors 1 place · today 19:38 EDT

Peacock Streaming Service Gets $3 Price Hike

NBC-owned streaming service Peacock is increasing its prices, and the ad-supported plan will soon be $3 more expensive. According to Variety, Peacock's ad-supported plan will be priced at $10.99 per month starting on July 23. The Premium Plus plan that features limited ads in live programming is also increasing in price from $13.99 to $16.99. Yearly pricing for the Premium plan will be $110, and the Premium Plus yearly price... Read more

352 fresh

Business Insider
Laura Italiano @ Business Insider 3 place · today 16:33 EDT

Blake Lively must turn over detailed business income records to Justin Baldoni

Lively has one week to turn over three years of records to her "It Ends With Us" costar as part of her sexual harassment and retaliation lawsuit. Read more

350 fresh

Eurogamer.net
Matt Wales @ Eurogamer.net 1 place · today 10:18 EDT

Silent Hill and Slitterhead creator teases new project, despite concerns about his advancing age

Silent Hill and Siren creator Keiichi Toyama has confirmed he and his team at Bokeh Game Studios is working it's next project, and it won't be a sequel to horror oddity Slitterhead. Read more Read more

317

The Verge
Jay Peters @ The Verge 1 place · today 19:52 EDT

Nintendo wants you to to join its next mysterious Switch Online playtest

Late last year, Nintendo hosted a mysterious Switch Online playtest, and on Thursday, the company announced that it would be doing another test as part of the “Nintendo Switch Online: Playtest Program” and that it will be opening applications soon. This second round will be a test of the “same service” as before. Last time, […] Read more

286 fresh

Gizmodo
Germain Lussier @ Gizmodo · today 18:00 EDT

Daisy Ridley’s Husband Cast in Adaptation of Former Reylo ‘Star Wars’ Fan Fiction

Tom Bateman will star alongside Lili Reinhart in an adaptation of the bestseller 'The Love Hypothesis' by Ali Hazelwood. Read more

278 fresh

GSMArena.com
GSMArena.com 1 place · today 16:02 EDT

Honor Magic V5 to hit its first European market on August 12

The Honor Magic V5, unveiled earlier this month, was initially only available in China. However, the Magic V5 was recently launched in Malaysia, and on August 12, it will make its debut in the first European country - Romania. It's unclear how many memory configurations and color options of the Honor Magic V5 will be available to Romanian customers, so we'll have to wait until August 12 for that and... Read more

242 fresh

CNET
Dianna Gunn @ CNET 2 place · today 18:55 EDT

How We Test Antivirus Software

This is the full process we use to test antivirus software and antivirus companies' cybersecurity suites. Read more

235 fresh

Business Insider
Peter Kafka @ Business Insider · today 18:19 EDT

Hey Donald Trump: Netflix says it loves making TV shows and movies in America.

Donald Trump has complained about media companies making movies outside the US. Netflix just emphasized how much of its production happens in the US. Read more

218 fresh

The most popular news from the same source for the last week
Slashdot Slashdot
Slashdot
EditorDavid @ Slashdot · 07/12/2025 18:34 EDT

'Firefox is Fine. The People Running It are Not'

"Firefox is dead to me," wrote Steven J. Vaughan-Nichols last month for The Register, complaining about everything from layoffs at Mozilla to Firefox's discontinuation of Pocket and Fakespot, its small market share, and some user complaints that the browser might be becoming slower. But a new rebuttal (also published by The Register) argues instead that Mozilla just has "a management layer that doesn't appear to understand what works for its... Read more

110

Slashdot
BeauHD @ Slashdot · 07/16/2025 18:30 EDT

Chinese Authorities Are Using a New Tool To Hack Seized Phones and Extract Data

An anonymous reader quotes a report from TechCrunch: Security researchers say Chinese authorities are using a new type of malware to extract data from seized phones, allowing them to obtain text messages -- including from chat apps such as Signal -- images, location histories, audio recordings, contacts, and more. In a report shared exclusively with TechCrunch, mobile cybersecurity company Lookout detailed the hacking tool called Massistant, which the company said... Read more

98

Slashdot
BeauHD @ Slashdot · 07/11/2025 03:00 EDT

Senator Calls Out Texas For Trying To Steal Shuttle From Smithsonian

Senator Dick Durbin questioned a Texas-led effort to move Space Shuttle Discovery from the Smithsonian to Space Center Houston, describing it as an expensive "heist" costing an estimated $305 million, not the $85 million initially budgeted. "This is not a transfer. It's a heist," said Durbin during a budget markup hearing before the Senate Appropriations Committee. "A heist by Texas because they lost a competition 12 years ago." In April,... Read more

93

Slashdot
EditorDavid @ Slashdot · 07/13/2025 07:34 EDT

DC's 'Brighter' Superman Movie Smashes Box Office Expectations

James Gunn's Superman "appears to be succeeding in rebooting DC Studios and its most iconic comic book franchise," writes The Hollywood Reporter, noting the film is "headed for a possible record domestic box office debut of $115 million to $120 million." Gunn is in a unique position, being both the film's writer-director and the co-head of the Warner Bros.-owned DC, which he co-runs with Peter Safran. Overseas, Superman is launching... Read more

87

Slashdot
EditorDavid @ Slashdot · 07/12/2025 23:34 EDT

Amelia Earhart's Airplane May Finally Have Been Found

An anonymous reader shared this report from Jalopnik: On July 2, the 88th anniversary of famed aviator Amelia Earhart's disappearance, Purdue University announced an expedition [which will launch in November] to confirm whether or not the wreckage of her plane has been found. Satellite imagery from a decade ago indicated the presence of something that sure looks plane-like under the waters of Nikumaroro Island, an uninhabited spit of land in... Read more

81

Slashdot
BeauHD @ Slashdot · 07/14/2025 18:10 EDT

An anonymous reader quotes a report from Ars Technica: Samuel Herman and Alexander Baciu never liked using Comcast's cable broadband. Now, the residents of Saline, Michigan, operate a fiber Internet service provider that competes against Comcast in their neighborhoods and has ambitions to expand. "All throughout my life pretty much, I've had to deal with Xfinity's bullcrap, them not being able to handle the speeds that we need," Herman told... Read more

78

Slashdot
EditorDavid @ Slashdot · 07/14/2025 07:34 EDT

COVID-19 Vaccine's mRNA Technology Adapted for First Antibiotic-Resistant Bacteria Vaccine

Researchers have created the world's first mRNA-based vaccine against a deadly, antibiotic-resistant bacterium — and they did it using the platform developed for COVID-19 vaccines. Medical Express publishes their announcement: The vaccine developed by the team from the Institute for Biological Research and Tel Aviv University is an mRNA-based vaccine delivered via lipid nanoparticles, similar to the COVID-19 vaccine. However, mRNA vaccines are typically effective against viruses like COVID-19 —... Read more

69

Slashdot
EditorDavid @ Slashdot · 07/12/2025 17:34 EDT

NVIDIA Warns Its High-End GPUs May Be Vulnerable to Rowhammer Attacks

Slashdot reader BrianFagioli shared this report from Nerds.xyz: NVIDIA just put out a new security notice, and if you're running one of its powerful GPUs, you might want to pay attention. Researchers from the University of Toronto have shown that Rowhammer attacks, which are already known to affect regular DRAM, can now target GDDR6 memory on NVIDIA's high-end GPUs when ECC [error correction code] is not enabled. They pulled this... Read more

68

Slashdot
BeauHD @ Slashdot · 07/15/2025 21:30 EDT

Thousands of Afghans Secretly Moved To Britain After Data Leak

The UK secretly relocated thousands of Afghans to the UK after their personal details were disclosed in one of the country's worst ever data breaches, putting them at risk of Taliban retaliation. The operation cost around $2.7 billion and remained under a court-imposed superinjunction until recently lifted. Reuters reports: The leak by the Ministry of Defence in early 2022, which led to data being published on Facebook the following year,... Read more

65

Slashdot
BeauHD @ Slashdot · 07/11/2025 06:00 EDT

Psilocybin Treatment Extends Cellular Lifespan, Improves Survival of Aged Mice

A new study found that psilocybin treatment significantly delayed cellular aging, extending human cell lifespan by over 50% and increasing survival in aged mice by 30%. The compound appeared to achieve these effects by reducing oxidative stress, preserving telomeres, and improving DNA repair. Neuroscience News reports: A newly published study in Nature Partner Journals' Aging demonstrates that psilocin, a byproduct of consuming psilocybin, the active ingredient in psychedelic mushrooms, extended... Read more

66

Most popular sources

  • You see 782 news out of 787.
  • Sources 61 out of 61.
Business Insider 24% 1
Gizmodo 13% 1
Android Authority 7% 1
Wired 7% 6
CNET 6% 3
View sources »

LIKE us on Facebook so you won't miss the most important news of the day!

17.07.2025 22:01
Last update: 21:56 EDT.
News rating updated: 04:50.

What is Times42?

Times42 brings you the most popular news from tech news portals in real-time chart.
Read about us in FAQ section.


Times42 © 2025