Discover ANY AI to make more online for less.

select between over 22,900 AI Tool and 17,900 AI News Posts.

<
New
Agents
Marketing
Video
Image
Music
Coding
Communication
Education
Travel
>

Apple study finds "a fundamental scaling limitation" in reasoning models' thinking abilities
Apple study finds "a fundamental scaling limitation" in reasoning models' thinking abilities

LLMs designed for reasoning, like Claude 3.7 and Deepseek-R1, are supposed to excel at complex problem-solving by simulating thought processes. But a new study by Apple researchers suggests that these models actually perform worse as tasks become more difficult and, in some cases, they "think" less.
The article Apple study finds "a fundamental scaling limitation" in reasoning models&#039; thinking abilities appeared first on THE DECODER.

Discover Copy
Rating

Innovation

Pricing

Technology

Usability

We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.

Apple's claims about large reasoning models face fresh scrutiny from a new study
Apple's claims about large reasoning models face fresh scrutiny from a new

<p><img width="1536" height="1024" src="https://the-decoder.com/wp-content/uploads/2025/06/graph_going_down_illustration.png" class="attachment-full size-fu [...]

Match Score: 86.78

The best Apple Watch in 2025
The best Apple Watch in 2025

<p>If you know you want an Apple Watch, but aren’t sure which one to get, this guide is here to explain the differences between the three models. The company’s flagship <a data-i13n=" [...]

Match Score: 78.96

So-called reasoning models are more efficient but not more capable than regular LLMs, study finds
So-called reasoning models are more efficient but not more capable than reg

<p><img width="1536" height="1024" src="https://the-decoder.com/wp-content/uploads/2025/04/rlvf_illustration_reinforcment_learning_tree.png" class="attachme [...]

Match Score: 69.16

The best Prime Day Apple deals on AirPods, iPads, MacBooks and more for the last day of the sale
The best Prime Day Apple deals on AirPods, iPads, MacBooks and more for the

<p>The last day of Amazon’s sale has arrived. Throughout the sale, we've been updating this with the best Apple <a data-i13n="cpos:1;pos:1" href="https://www.engadget.com/dea [...]

Match Score: 68.86

The best Prime Day Apple deals on AirPods, iPads, MacBooks and more for day two
The best Prime Day Apple deals on AirPods, iPads, MacBooks and more for day

<p>You won’t find many discounts on Apple’s own website — but that doesn’t mean you have to pay full price for a new iPad or pair of AirPods. The second day of Amazon’s July sale is he [...]

Match Score: 65.28

The best Prime Day Apple deals on AirPods, iPads, MacBooks and more for day three of Amazon's sale
The best Prime Day Apple deals on AirPods, iPads, MacBooks and more for day

<p>Day three of Amazon’s sale is here and this guide rounds up the best Apple <a data-i13n="cpos:1;pos:1" href="https://www.engadget.com/deals/the-best-amazon-prime-day-deals [...]

Match Score: 65.28

Apple WWDC 2025 preview: iOS updates, macOS, AI and other news we expect next week
Apple WWDC 2025 preview: iOS updates, macOS, AI and other news we expect ne

<p><a href="https://www.yahoo.com/organizations/apple/" data-autolinker-wiki-id="Apple_Inc." data-original-link="">Apple</a>&#39;s big 2025 software [...]

Match Score: 64.45

WWDC 2025: What we expect Apple to reveal including new iOS, macOS, Apple Intelligence and more
WWDC 2025: What we expect Apple to reveal including new iOS, macOS, Apple I

<p><a href="https://www.yahoo.com/organizations/apple/" data-autolinker-wiki-id="Apple_Inc." data-original-link="">Apple</a>&#39;s big 2025 software [...]

Match Score: 63.68

Anthropic study finds language models often hide their reasoning process
Anthropic study finds language models often hide their reasoning process

<p><img width="1536" height="1024" src="https://the-decoder.com/wp-content/uploads/2025/04/chain_of_thought_going_wrong.png" class="attachment-full size-ful [...]

Match Score: 63.66