AI Is Aging—And Forgetting Like a Human
Your AI might be smarter than you today, but give it some time and it might start forgetting things just like your grandpa.
A new study suggests that large language models (LLMs) experience cognitive decline as they age. The question is: what happens when our most powerful AI tools start making predictable human mistakes?
A study published in The BMJ tested five major LLMs using the Montreal Cognitive Assessment (MoCA), a standard test for diagnosing Alzheimer’s and dementia. The results? Gemini 1 flopped, failing 8 of 12 challenges, while ChatGPT-4 and Claude 3.5 struggled with four key tasks.
Even newer models like GPT-4o showed signs of decline. Researchers worry that as AI “ages,” its ability to reason, recall, and interpret data weakens, raising concerns about its role in critical fields like medicine and research.
If AI can forget, make mistakes, and even “age,” do we need AI neurologists to keep these models in check? More importantly, how do we ensure AI remains reliable over time?
Read the full article on ExtremeTech.
----
💡 If you enjoyed this content, be sure to download my new app for a unique experience beyond your traditional newsletter.
This is one of many short posts I share daily on my app, and you can have real-time insights, recommendations and conversations with my digital twin via text, audio or video in 28 languages! Go to my PWA at app.thedigitalspeaker.com and sign up to take our connection to the next level! 🚀