Mark Zuckerberg-owned Meta rolled out its Meta AI chatbot to WhatsApp, Instagram and other platforms last month. The artificial intelligence (AI) chatbot appears to be struggling with a basic mathematics question.
When asked ‘which is bigger 9.9 or 9.11’, Meta AI on WhatsApp responded ‘9.11 is bigger than 9.9’. On further asking to explain why 9.11 is bigger than 9.9, the chatbot replied “Because 9.9 is smaller than 9.11 by a margin of 0.02.When comparing decimal numbers, we look at the digits after the decimal point, and in this case, 0.02 is a small positive difference that makes 9.11 slightly larger than”.
On further questioning, the AI chatbot “But 9.9 is 9.90 — so isn’t that greater than 9.11”, it replied “You are absolutely right! I apologize for my earlier mistake. 9.9 is indeed equal to 9.90, and 9.90 is greater than 9.11. Thank you for catching that error”.
Check the Meta AI screenshots of the query
When asked ‘which is bigger 9.9 or 9.11’, Meta AI on WhatsApp responded ‘9.11 is bigger than 9.9’. On further asking to explain why 9.11 is bigger than 9.9, the chatbot replied “Because 9.9 is smaller than 9.11 by a margin of 0.02.When comparing decimal numbers, we look at the digits after the decimal point, and in this case, 0.02 is a small positive difference that makes 9.11 slightly larger than”.
On further questioning, the AI chatbot “But 9.9 is 9.90 — so isn’t that greater than 9.11”, it replied “You are absolutely right! I apologize for my earlier mistake. 9.9 is indeed equal to 9.90, and 9.90 is greater than 9.11. Thank you for catching that error”.
Check the Meta AI screenshots of the query
How other AI platforms replied to the query
OpenAI’s ChatGPT, according to screenshots shared by users on a community forum, responded with the same answer as MetaAI saying that ‘9.11 is bigger than 9.9’. However, it seems to have corrected later as when we checked, the AI chatbot replied “9.9 is bigger than 9.11 because 9.9 is closer to 10, while 9.11 is just slightly over 9”.
Check the OpenAI’s ChatGPT screenshot here
Anthropic’s ClaudeAI also got the answer wrong.