AI systems lack “quite basic skills” despite their advanced models, including struggling to tell the time or read dates off calendars, Scottish researchers have shown.
A team from the University of Edinburgh has shown that state-of-the-art AI models are unable to reliably interpret clock-hand positions or correctly answer questions about dates on calendars.
Rohit Saxena, of the University of Edinburgh’s School of Informatics, said: “Most people can tell the time and use calendars from an early age. Our findings highlight a significant gap in the ability of AI to carry out what are quite basic skills for people.
“These shortfalls must be addressed if AI systems are to be successfully integrated into time-sensitive, real-world applications, such as scheduling, automation and assistive technologies.”
The researchers tested if AI systems that process text and images – known as multimodal large language models (MLLMs) – can answer time-related questions by looking at a picture of a clock or a calendar.
They also tested various clock designs, including some with Roman numerals, with and without second hands, and different coloured dials.
The findings show that AI systems, at best, recognised clock-hand positions correctly less than a quarter of the time.
Mistakes were more common when clocks had Roman numerals or stylised clock hands.
AI systems also did not perform any better when the second hand was removed, suggesting there are basic issues with hand detection and angle interpretation.
When asked a range of calendar-based questions – such as identifying holidays and working out past and future dates) – researchers found that even the best-performing AI model got date calculations wrong one-fifth of the time.
Aryo Gema, also of the School of Informatics, said: “AI research today often emphasises complex reasoning tasks, but ironically, many systems still struggle when it comes to simpler, everyday tasks.
“Our findings suggest it’s high time we addressed these fundamental gaps. Otherwise, integrating AI into real-world, time-sensitive applications might remain stuck at the eleventh hour.”
This indicates that while AI models can perform complex tasks such as writing essays and generating art, they have yet to master some skills that humans carry out with ease.
Understanding analogue clocks and calendars requires a combination of spatial awareness, context and basic maths, which remains a challenge for AI.
According to the team, overcoming this could enable AI systems to power time-sensitive applications like scheduling assistants, autonomous robots and tools for people with visual impairments.
The findings are reported in a peer-reviewed paper that will be presented at the Reasoning and Planning for Large Language Models workshop at The Thirteenth International Conference on Learning Representations (ICLR) in Singapore on April 28, 2025.
