AI models struggle to identify nonsense, says study


Researchers put nine AI models through their paces, firing hundreds of pairs of sentences at them and asking which were likely to be heard in everyday speech. — AFP Relaxnews

The AI models that power chatbots and other applications still have difficulty distinguishing between nonsense and natural language, according to a study released on Thursday.

The researchers at Columbia University in the United States said their work revealed the limitations of current AI models and suggested it was too early to let them loose in legal or medical settings.

The Star Christmas Special Promo: Save 35% OFF Yearly. T&C applies.

Monthly Plan

RM 13.90/month

Best Value

Annual Plan

RM 12.33/month

RM 8.02/month

Billed as RM 96.20 for the 1st year, RM 148 thereafter.

Follow us on our official WhatsApp channel for breaking news alerts and key updates!

Next In Tech News

Tech influencer Lamarr Wilson dies by suicide at 48
Sam Altman’s cringe AI thirst trap says a lot about the future of OpenAI
Italy regulator fines Apple $115 million for alleged App Store privacy violations
The rise of deepfake cyberbullying poses a growing problem for schools
As US battles China on AI, some companies choose Chinese
Boys at her school shared AI-generated, nude images of her. After a fight, she was the one expelled
Banks in M'sia urge customers to update browsers and mobile OS for enhanced security
Waymos froze, blocked traffic during San Francisco power outage
Cancer stole her voice. She used AI, curse words and kids’ books to get it back
Once a gamble in the desert, electric grid batteries are everywhere

Others Also Read