welcome
About us
Newsletter
News Widget
Media Inquiries

Summary

AI Reasoning Models Misunderstood

This is a news story, published by Live Science, that relates primarily to AI news.

News about Ai research

For more Ai research news, you can click here:

more Ai research news

Live Science news

For more news from Live Science, you can click here:

more news from Live Science

About the Otherweb

Otherweb, Inc is a public benefit corporation, dedicated to improving the quality of news people consume. We are non-partisan, junk-free, and ad-free. We use artificial intelligence (AI) to remove junk from your news feed, and allow you to select the best tech news, business news, entertainment news, and much more. If you like this article about Ai research, you might also like this article about

large reasoning models

. We are dedicated to bringing you the highest-quality news, junk-free and ad-free, about your favorite topics. Please come every day to read the latest artificial general intelligence news, imminent machine intelligence claim news, news about Ai research, and other high-quality news about any topic that interests you. We are working hard to create the best news aggregator on the web, and to put you in control of your news feed - whether you choose to read the latest news through our website, our news app, or our daily newsletter - all free!

AI researchers
Live Science

Live Science

•

Technology

Technology

AI reasoning models aren’t as smart as they were cracked up to be, Apple study claims

Live Science
Summary
Nutrition label

78% Informative

Apple researchers say AI reasoning models aren't as smart as they've been made out to be.

They say their accuracy collapses when tasks get too complex.

Reasoning models are an attempt to further boost AI 's accuracy using a process known as "chain-of-thought" This process is rooted in statistical guesswork instead of any real understanding.

Some AI researchers have heralded the study as a necessary heaping of cold water on grandiose claims about current AI tools' ability to one day become superintelligent.

But the researchers do highlight key limitations to their study, including that the problems only represent a "narrow slice" of the potential reasoning tasks that the models could be assigned.

Apple is instead prioritizing development of on-device, efficient AI over large reasoning models.

VR Score

85

Informative language

88

Neutral language

47

Article tone

informal

Language

English

Language complexity

65

Offensive language

not offensive

Hate speech

not hateful

Attention-grabbing headline

not detected

Known propaganda techniques

not detected

Time-value

long-living

External references

11

https://x.com/pmddomingos/status/1931767975000088717?s=46https://x.com/burkov/status/1931907831894036515?s=46https://cdn.openai.com/pdf/2221c875-02dc-4789-800b-e7758f3722c1/o3-and-o4-mini-system-card.pdfhttp://washingtonhttps://www.tomsguide.com/ai/apple-intelligence/apple-is-2-years-behind-on-ai-but-heres-why-i-think-it-will-still-end-up-aheadhttps://en.wikipedia.org/wiki/Tower_of_Hanoihttps://www.bloomberg.com/news/newsletters/2024-10-20/apple-s-latest-ipad-mini-highlights-ai-advantage-sonos-considers-new-headphones-m2hkz4mn?srnd=undefinedhttps://www.windowscentral.com/software-apps/we-have-already-achieved-agi-openai-employee-claimshttps://arxiv.org/abs/2501.08156https://getstream.io/blog/reasoning-llms/https://linktr.ee/burkov

Source diversity

10

x.comcdn.openai.comwashingtonwww.tomsguide.comen.wikipedia.orgwww.bloomberg.comwww.windowscentral.comarxiv.orggetstream.iolinktr.ee

Affiliate links

1

https://go.redirectingat.com/?id=92X1590019&xcust=livescience_us_5164315712481417833&xs=1&url=https%3A%2F%2Fmachinelearning.apple.com%2Fresearch%2Fillusion-of-thinking&sref=https%3A%2F%2Fwww.livescience.com%2Ftechnology%2Fartificial-intelligence%2Fai-reasoning-models-arent-as-smart-as-they-were-cracked-up-to-be-apple-study-claims
Read full article