惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

C
Cisco Blogs
Schneier on Security
Schneier on Security
T
Tor Project blog
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
T
Tenable Blog
C
Cyber Attacks, Cyber Crime and Cyber Security
T
Threat Research - Cisco Blogs
C
CERT Recently Published Vulnerability Notes
Security Latest
Security Latest
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
NISL@THU
NISL@THU
L
Lohrmann on Cybersecurity
Scott Helme
Scott Helme
Webroot Blog
Webroot Blog
Project Zero
Project Zero
Google Online Security Blog
Google Online Security Blog
The Last Watchdog
The Last Watchdog
Spread Privacy
Spread Privacy
Hacker News: Ask HN
Hacker News: Ask HN
PCI Perspectives
PCI Perspectives
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
W
WeLiveSecurity
Attack and Defense Labs
Attack and Defense Labs
D
Darknet – Hacking Tools, Hacker News & Cyber Security
N
News | PayPal Newsroom
Help Net Security
Help Net Security
The Hacker News
The Hacker News
H
Heimdal Security Blog
O
OpenAI News
S
Security @ Cisco Blogs
N
News and Events Feed by Topic
Cyberwarzone
Cyberwarzone
Simon Willison's Weblog
Simon Willison's Weblog
G
GRAHAM CLULEY
www.infosecurity-magazine.com
www.infosecurity-magazine.com
博客园 - 叶小钗
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
Hacker News - Newest:
Hacker News - Newest: "LLM"
T
Tailwind CSS Blog
大猫的无限游戏
大猫的无限游戏
A
Arctic Wolf
I
Intezer
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
S
Security Affairs
P
Proofpoint News Feed
S
Secure Thoughts
腾讯CDC
Google DeepMind News
Google DeepMind News
量子位
罗磊的独立博客

Tech Archives - VICE

This VR App Teaches You to Dance Without Letting Anyone Watch You Struggle The Strange Case of Elias Thorne, the Imaginary Man AI Chatbots Are Obsessed With AI-Powered Teddy Bears for Kids Are Here, and Experts Say They Could Do More Harm Than Good Researchers Put AI Chatbots in Charge of a Simulated World. This One Destroyed Everything in Just 4 Days. Scientists Created the Optimal Robot, and You’ll Never Guess What It Looks Like The AI Boom Is Taking Over the U.S. Power Grid, and This Map Shows Where It’s Happening Someone Made a Fake Wikipedia for AI Hallucinations, and It’s Basically the Internet Eating Itself I Built My Perfect AI Companion. She’s Kind of Great ChatGPT Just Got a Weird New List of Forbidden Topics (Including Gremlins) Apple Leaks Reveal Controversial Details and Design of Foldable iPhone Ultra Apple's Tim Cook Era Is Ending. Here’s What Tech Fans Want Next. Bitcoin Creator Satoshi Nakamoto’s True Identity Has Been Revealed. Or Has It? Who’s Really Driving Your Tesla Robotaxi? $300,000 Robot Dogs Are Guarding AI Data Centers. Are We Doomed, Chat? OpenAI Is Pulling Back on Its Erotic Chatbot. Here’s Why. Sonos Trueplay’s Generic Tuning Works Better Than the ‘Custom’ Option You Should Probably Be Using Vertical Browser Tabs Open-Back or Closed-Back Headphones? Here’s the One You Actually Need. Is Your E-Bike Battery Bad? Here’s How to Tell. Mini Sports Cars for Adults Are a Thing Now, and They Can Hit 50 MPH How to Buy Your First Ebike: A Guide
Here’s How Long You Can Use AI Before Your Brain Starts Rotting, According to Scientists
Luis Prada · 2026-05-12 · via Tech Archives - VICE

Sure, by now we all know that overusing AI can rot your brain. If you stop doing the critical thinking needed to solve your own problems and start outsourcing everything to a chatbot, eventually your mental muscles are going to atrophy a little. So all you have to do is not rely on it too much, and problem solved, right? Nah.

According to a new study from researchers at Carnegie Mellon University, Massachusetts Institute of Technology, University of Oxford, and University of California, Los Angeles, it may only take about 10 minutes of AI use for your brain to start rotting. Yikes.

Videos by VICE

The researchers divided participants into groups and gave them reading comprehension and math problems. One group worked normally. The other received help from an AI chatbot powered by OpenAI’s GPT-5 model. Then, without warning, researchers removed the AI assistance midway through the tests. Things got hilariously bleak, fast.

(Illustration via Paper Trident / Getty Images)

People who had relied on AI saw their performance drop almost immediately, by about 20 percent compared to people who solved the problems on their own from the start. They were nearly twice as likely to skip questions altogether rather than power through them. The researchers saw the same pattern regardless of whether it was a math or a reading task. Researchers think that once people get used to AI doing the heavy lifting, they lose the willingness to figure out solutions to hard problems on their own.

The damage was worst among people who used AI to generate answers without putting in any effort whatsoever. The people who used AI more like a tutor, asking it for hints and nudges in the right direction rather than complete solutions, performed a little better once the AI assistance vanished.

All of this presents a major problem for AI being integrated into every facet of life where critical thinking skills are necessary, such as schools and workplaces. The researchers say that the desire to offload so much of our own thinking onto AI is disengaging us from the kind of thinking that allows people to learn to solve difficult problems at all.