Apple Researchers Just Released a Damning Paper That Pours Water on the Entire AI Industry
Researchers at Apple have released an eyebrow-raising paper that throws cold water on the "reasoning" capabilities of the latest, most powerful large language models.
In the paper, a team of machine learning experts makes the case that the AI industry is grossly overstating the ability of its top AI models, including OpenAI's o3, Anthropic's Claude 3.7, and Google's Gemini.
In particular, the researchers assail the claims of companies like OpenAI that their most advanced models can now "reason" — a supposed capability that the Sam Altman-led company has increasingly leaned on over the past year for marketing purposes — which the Apple team characterizes as merely an "illusion of thinking."
It's a particularly noteworthy finding, considering Apple has been accused of falling far behind the competition in the AI space. The company has chosen a far more careful path to integrating the tech in its consumer-facing products — with some seriously mixed results so far.
In theory, reasoning models break down user prompts into pieces and use sequential "chain of thought" steps to arrive at their answers. But now, Apple's own top minds are questioning whether frontier AI models simply aren't as good at "thinking" as they're being made out to be.
"While these models demonstrate improved performance on reasoning benchmarks, their fundamental capabilities, scaling properties, and limitations remain insufficiently understood," the team wrote in its paper.
The authors — who include Samy Bengio, the director of Artificial Intelligence and Machine Learning Research at the software and hardware giant — argue that the existing approach to benchmarking "often suffers from data contamination and does not provide insights into the reasoning traces' structure and quality."
By using "controllable puzzle environments," the team estimated the AI models' ability to "think" — and made a seemingly damning discovery.
"Through extensive experimentation across diverse puzzles, we show that frontier [large reasoning models] face a complete accuracy collapse beyond certain complexities," they wrote.
Thanks to a "counter-intuitive scaling limit," the AIs' reasoning abilities "declines despite having an adequate token budget."
Put simply, even with sufficient training, the models are struggling with problem beyond a certain threshold of complexity — the result of "an 'overthinking' phenomenon," in the paper's phrasing.
The finding is reminiscent of a broader trend. Benchmarks have shown that the latest generation of reasoning models is more prone to hallucinating, not less, indicating the tech may now be heading in the wrong direction in a key way.
Exactly how reasoning models choose which path to take remains surprisingly murky, the Apple researchers found.
"We found that LRMs have limitations in exact computation," the team concluded in its paper. "They fail to use explicit algorithms and reason inconsistently across puzzles."
The researchers claim their findings raise "crucial questions" about the current crop of AI models' "true reasoning capabilities," undercutting a much-hyped new avenue in the burgeoning industry.
That's despite tens of billions of dollars being poured into the tech's development, with the likes of OpenAI, Google, and Meta, constructing enormous data centers to run increasingly power-hungry AI models.
Could the Apple researchers' finding be yet another canary in the coalmine, suggesting the tech has "hit a wall"?
Or is the company trying to hedge its bets, calling out its outperforming competition as it lags behind, as some have suggested?
It's certainly a surprising conclusion, considering Apple's precarious positioning in the AI industry: at the same time that its researchers are trashing the tech's current trajectory, it's promised a suite of Apple Intelligence tools for its devices like the iPhone and MacBook.
"These insights challenge prevailing assumptions about LRM capabilities and suggest that current approaches may be encountering fundamental barriers to generalizable reasoning," the paper reads.
More on AI models: Car Dealerships Are Replacing Phone Staff With AI Voice Agents
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
33 minutes ago
- Yahoo
5 AI stocks to consider buying and holding for the long term
Many AI applications are still in development, offering ground-floor buying opportunities in their stocks. Below are some established companies that five of contract writers like as investments to consider buying to capitalise on this transformational technology. What it does: Alphabet is a global technology company best known for Google, YouTube, Android, and cloud services. By Mark Hartley. When considering an AI investment for the long term, Google's parent company Alphabet (NASDAQ: GOOG) stands out. It has emerged as a key player in the AI space, leveraging its vast data resources and computational power to dig deep roots into the industry. Through DeepMind and its Gemini AI models, Alphabet is at the forefront of generative AI development. Google Cloud offers scalable AI tools and infrastructure for businesses, while AI enhancements in products like Search, Gmail, and YouTube are well-positioned to benefit from advertising revenue. Alphabet's expansive ecosystem gives it a strategic advantage in training and deploying AI models at scale. A significant risk, however, lies in the potential disruption of its core search business. As AI chatbots and generative search become more prevalent, traditional search advertising could face margin pressure. Additionally, if faces increased regulatory scrutiny on data usage, antitrust concerns and competition from rivals like Microsoft and Amazon. Mark Hartley doesn't own shares in any of the stocks mentioned. What it does: Cellebrite is the global leader in decrypting mobile phones and other devices supporting digital forensic investigations. By Zaven Boyrazian. Many AI stocks today are unproven. That's why I prefer established players leveraging AI to improve their existing mission-critical products like Cellebrite (NASDAQ:CLBT). Cellebrite specialises in extracting encrypted data from mobile phones and other devices aiding law enforcement and enterprises in criminal and cybersecurity investigations. Over 90% of crime commited today has a digital element. And when it comes to decrypting mobile phones, Cellebrite is the global gold standard. The company is now leveraging AI to analyse encrypted data – drastically accelerating a task that's historically been increadibly labour intensive identifying patterns, discovering connections, and establishing leads. Most of Cellebrite's revenue comes from law enforcement, exposing Cellebrite to the risk of budget cuts. In fact, fears of lower US federal spending is why the stock dropped sharply in early 2025. And with a premium valuation, investors can expect more volatility moving forward. But in the long run, Cellebrite has what it takes to be an AI winner in my mind. That's why I've already bought shares. Zaven Boyrazian owns shares in Cellebrite. What it does: Dell Technologies provides a broad range of IT products and services and is an influential player in AI. By Royston Wild. Dell Technologies (NYSE:DELL) isn't one of the more fashionable names in the realm of artificial intelligence (AI). The good news is that this means it trades at a whopping discount to many of its peers. For this financial year (to January 2026), City analysts think earnings will soar 41% year on year, leaving it on a price-to-earnings (P/E) multiple of 12.6 times. Such readings are as rare as hen's teeth in the high-growth tech industry. In addition, Dell shares also trade on a price-to-earnings growth (PEG) ratio of 0.3 for this year. Any reading below 1 implies a share is undervalued. These modest readings fail to reflect the exceptional progress the company's making in AI, in my opinion. Indeed, Dell last month raised guidance for the current quarter as it announced 'unprecedented demand for our AI-optimised servers' during January-March. It booked $12.1bn in AI orders in the last quarter alone, beating the entire total for the last financial year. Dell is a major supplier of server infrastructure that let Nvidia's high-power chips do their thing. Dell's shares could sink if unfavourable developments in the ongoing tariff wars transpire. But the company's low valuation could help limit the scale of any falls. Royston Wild does not own shares in Dell or Nvidia. What it does: Salesforce is a customer relationship management (CRM) software company that is developing AI agents. By Edward Sheldon, CFA. We've all seen the potential of artificial intelligence (AI) in recent years. Using apps like ChatGPT and Gemini, we can do a lot of amazing things today. These apps are just the start of the AI story, however. I expect the next chapter to be about AI agents – software programmes that can complete tasks autonomously and increase business productivity exponentially. One company that is active in this space is Salesforce (NYSE: CRM). It's a CRM software company that has recently developed an agentic AI offering for businesses called 'Agentforce'. It's still early days here. But already the company is having a lot of success with this offering, having signed up 8,000 customers since the product's launch last October. Now, Salesforce is not the only company developing AI agents. So, competition from rivals is a risk. I like the fact that the company's software is already embedded in over 150,000 organisations worldwide though. This could potentially give it a major competitive advantage in the agentic AI race. Edward Sheldon has positions in Salesforce. What it does: Salesforce is a cloud-based software company specialising in customer relationship management, helping businesses manage sales, marketing, support, and data. By Ben McPoland. I think Salefsforce (NYSE: CRM) looks well set up to benefit in the age of AI. Specifically, its Agentforce platform, which lets businesses deploy AI agents to handle various tasks, could be the company's next big growth engine. By the end of April, it had already closed over 8,000 deals, just six months after launching Agentforce. Half of those were paid deals, taking its combined data cloud and AI annual recurring revenue above $1bn. Granted, that looks like small potatoes set against the $41.2bn in sales it's expected to generate this fiscal year. But it's still very early days, and management reckons the digital labour market opportunity could run into the trillions of dollars. Of course, it's always best to treat such mind-boggling projections with a healthy dose of scepticism. And the company does face stiff competition in the AI agent space, especially from Microsoft and ServiceNow. Nevertheless, I'm bullish here. Salesforce is already deeply embedded in sales, service, and marketing. Its AI agents slot into existing workflows, which I think will prove to be a big advantage over unproven AI upstarts. Ben McPoland owns shares of Salesforce. The post 5 AI stocks to consider buying and holding for the long term appeared first on The Motley Fool UK. More reading 5 Stocks For Trying To Build Wealth After 50 One Top Growth Stock from the Motley Fool John Mackey, former CEO of Whole Foods Market, an Amazon subsidiary, is a member of The Motley Fool's board of directors. Suzanne Frey, an executive at Alphabet, is a member of The Motley Fool's board of directors. The Motley Fool UK has recommended Alphabet, Amazon, Cellebrite, Microsoft, Nvidia, and Salesforce. Views expressed on the companies mentioned in this article are those of the writer and therefore may differ from the official recommendations we make in our subscription services such as Share Advisor, Hidden Winners and Pro. Here at The Motley Fool we believe that considering a diverse range of insights makes us better investors. Motley Fool UK 2025 Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
CNET
an hour ago
- CNET
When Will the iPhone 17 Be Released? We're Following All the Rumors and Leaks
Of all the questions about the rumored iPhone 17, there's one that could settle all others: When is the release date? All of the predictions and speculation about battery power, colors, price and more will be resolved when Apple releases the new iPhone, including the rumored iPhone Air. But even the release date is the subject of leaks and rumors. We've sifted through the whispers, analysis and conjecture so you can know when the new iPhone will be released and when you can expect to get your hands on one. Read more: Ready to Buy a New iPhone? Here's Why You Should Wait Watch this: Hey, Apple: Steal These S25 Edge Features for a Skinny iPhone 04:33 When will the iPhone 17 be released? For nearly a decade, Apple has announced its new iPhone lineup in early September. (The only exception was during COVID, when the release was pushed back to Oct. 23, 2020, for the iPhone 12 and 12 Pro and Nov. 13, 2020, for the iPhone 12 Mini and 12 Pro Max.) Historically, Apple has made the announcement on the first Tuesday of September after Labor Day. However, the first Tuesday in 2025 is the day after Labor Day, so Apple could push the dates for its iPhone event to Wednesday, Sept. 3 or Tuesday, Sept. 9. That would mean a release date of Sept. 12 or 19. And because the new iPhone typically becomes available for preorder the Friday after, the preorder date could be either Sept. 5 or 12. Here's a chart for the potential dates based on past schedules. These are not official dates from Apple: Potential iPhone 17 schedule Announcement Preorder Release Wednesday, Sept. 3 Sept. 5 Sept. 12 Tuesday, Sept. 9 Sept. 12 Sept. 19 Will all of the new iPhones be released in the fall? Based on last year's release, Apple may release everything in the fall except its least expensive option -- this year, the iPhone 16E. The iPhone 16E was released in February, and Apple is widely expected to follow the same format for the rumored iPhone 17. That would mean the iPhone 17 Pro Max, iPhone 17 Pro, iPhone 17 Air and the iPhone 17 base model -- if that's the lineup -- would be released in September. The iPhone 17E -- if it exists -- would be released in February. Apple's future iPhone release dates Apple is expected to change its release format with the rumored iPhone 18. Reports suggest that Apple will only release higher-end models in fall 2026 -- iPhone 18 Pro, Pro Max, Air and a rumored new foldable iPhone -- and release the rest of the line in winter 2027. Why does Apple split iPhone release dates? By pushing its top-of-the-line Pro and Pro Max models in September, Apple can capture much of the holiday shopping season. Releasing the more basic models in the winter allows a second crest of excitement, but diehard fans and holiday shoppers will have already spent their money on the pricier models in the fall.
Tom's Guide
an hour ago
- Tom's Guide
I've been using the new iOS 26 Camera app — and it finally address by biggest annoyance
Apple's certainly putting a lot of effort into overhauling the iPhone's look in its upcoming iOS 26 release, which should officially arrive this fall alongside its iPhone 17 announcement. In the interim, though, I've been using the iOS 26 developer beta to get a sneak peek into what Apple's packing into its iPhone software update. I will say that I'm particularly happy that the iPhone Camera app is getting a big makeover, but I'm even more excited about one particular change that makes it much more conducive to my workflow when shooting photos and videos. In addition to adopting all the visual elements of Apple's new Liquid Glass interface, the iOS 26 camera app is filled with new features that finally elevates it to nearly the same usability I get in some of the best Android phones and their camera apps. After trying out the Camera app on iPhone for the past week, here's everything new and different about it in iOS 26. And I know you'll be excited for these changes as well. The biggest complaint I've had with the iPhone Camera app is how some of the camera's settings are buried in the general Settings menu. With iOS 26, however, Apple is making those controls accessible from the app itself — rather than going into the Settings app and then to the camera settings from there. To put it another way, I'm now able to quickly (and conveniently) switch the video recording resolution from within the Camera app. This one simple change makes a huge difference in how I use the iPhone Camera app going forward because I don't have to exit out of the app to change them. With photos, I can switch between JPEG and RAW formats — in addition to choosing 24MP or 48MP. It gets better in my opinion with video recording — now I can switch the format, resolution, and frame rate. When you shoot as much video professionally as I do, having access to these controls from within the app iteself is much more intuitive and saves me time. The only options that still require me to go to the general settings menu to activate are the grid and level guides. I can live with this because generally speaking, I don't ever disable them. Get instant access to breaking news, the hottest reviews, great deals and helpful tips. With its Liquid Glass material design, the iOS 26 Camera app looks cleaner than before, as the only options that show up after launching the app are Photo and Video. By scrolling to the left and right of this, I can still switch between all the other modes — like portrait, panoramic, slo-mo, and more. In order to access some of the other settings within each respective mode, you have to perform a swipe up gesture from the bottom. When I do this in Photo mode, I can access settings for the flash, live photos, timer, exposure, styles, filter, and aspect ratio. I can also access these tools as well by tapping on the icon with six dots in the upper right corner. If you happen to own an iPhone 16 model offering the Camera Control, you'll want to adjust this one setting. That's because by default, Apple has disabled many of the Camera Control options. Obviously, pressing down on the Camera Control instantly launches the Camera app, but swipe gestures only allow me to switch between its four different cameras. Although it might seem like a zoom control, it really isn't because it's only switching between the different cameras — so I can't get to something like 3.5x zoom using it. In order to access Camera Control's full potential, I had to go into the Camera Control settings in the general settings menu and enable "camera adjustments" for exposure, depth, zoom, styles, and tone control. I honestly don't mind this setting being disabled by default because in my experience, it actually slows down my workflow rather than helping it. I'm really happy that Apple has finally listened and fixed my biggest gripe about the iPhone Camera app. Now I'm no longer annoyed about exiting the app just to adjust some of the camera settings. However, I still crave even more functionality out of the app. In particular, I would like Apple to open up manual controls to let me adjust the ISO, shutter speed, and focus with the camera — much like how some Android phones let me change those settings in their Pro or manual modes. iPhone users, still need to use a third party camera app to get these controls, even with iOS 26. Apart from that, though, the iOS 26 Camera app is much more functional and cleaner looking than ever before. I'm looking forward to using it with the iOS 26 beta and beyond.
