Welcome to DU! The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards. Join the community: Create a free account Support DU (and get rid of ads!): Become a Star Member Latest Breaking News Editorials & Other Articles General Discussion The DU Lounge All Forums Issue Forums Culture Forums Alliance Forums Region Forums Support Forums Help & Search

milestogo

(23,200 posts)
Sun Feb 16, 2025, 12:21 PM Feb 2025

Older AI models show signs of cognitive decline, study shows

By Drew Turney

Older chatbots, just like people, show signs of cognitive impairment, failing on several important metrics in a test normally used on human patients.


People increasingly rely on artificial intelligence (AI) for medical diagnoses because of how quickly and efficiently these tools can spot anomalies and warning signs in medical histories, X-rays and other datasets before they become obvious to the naked eye. But a new study published Dec. 20, 2024 in the BMJ raises concerns that AI technologies like large language models (LLMs) and chatbots, like people, show signs of deteriorated cognitive abilities with age.

"These findings challenge the assumption that artificial intelligence will soon replace human doctors," the study's authors wrote in the paper, "as the cognitive impairment evident in leading chatbots may affect their reliability in medical diagnostics and undermine patients' confidence."

Scientists tested publicly available LLM-driven chatbots including OpenAI's ChatGPT, Anthropic's Sonnet and Alphabet's Gemini using the Montreal Cognitive Assessment (MoCA) test — a series of tasks neurologists use to test abilities in attention, memory, language, spatial skills and executive mental function.

MoCA is most commonly used to assess or test for the onset of cognitive impairment in conditions like Alzheimer's disease or dementia. Subjects are given tasks like drawing a specific time on a clock face, starting at 100 and repeatedly subtracting seven, remembering as many words as possible from a spoken list, and so on. In humans, 26 out of 30 is considered a passing score (ie the subject has no cognitive impairment.

Read more: https://www.livescience.com/technology/artificial-intelligence/older-ai-models-show-signs-of-cognitive-decline-study-shows

Not satire.

2 replies = new reply since forum marked as read
Highlight: NoneDon't highlight anything 5 newestHighlight 5 most recent replies
Older AI models show signs of cognitive decline, study shows (Original Post) milestogo Feb 2025 OP
Fascinating. Thanks for sharing this. Oopsie Daisy Feb 2025 #1
Read the rebuttals in the comments. snot Feb 2025 #2

snot

(11,848 posts)
2. Read the rebuttals in the comments.
Sun Feb 16, 2025, 01:01 PM
Feb 2025

At best, the info given in the original story is inadequate to permit evaluation of its conclusion.

Kick in to the DU tip jar?

This week we're running a special pop-up mini fund drive. From Monday through Friday we're going ad-free for all registered members, and we're asking you to kick in to the DU tip jar to support the site and keep us financially healthy.

As a bonus, making a contribution will allow you to leave kudos for another DU member, and at the end of the week we'll recognize the DUers who you think make this community great.

Tell me more...

Latest Discussions»General Discussion»Older AI models show sign...