Even as ChatGPT's knowledge is limited to September 2021, questions on current events were not answered properly.
OpenAI's AI chatbot ChatGPT has failed to clear the Indian Civil Services Examination, conducted by Union Public Service Commission (UPSC), one of the toughest in the world, according to media reports on Saturday.
Launched in November 2022, the chatbot has gained immense popularity. It also cleared several exams in the US, including the US Medical Licensing Exam (USMLE) and other MBA exams. It also managed to clear Google Coding Interview for Level 3 Engineers.
To check its proficiency, Bengaluru-based Analytics India Magazine subjected it to clear the Civil service exams with questions ranging from topics such as Geography, Economy, History, Ecology, General Science and current affairs.
The Magazine asked ChatGPT all the 100 questions from Question Paper 1 (Set A) from UPSC Prelims 2022.
"Only 54 of them were correctly answered by ChatGPT," it reported.
Even as ChatGPT's knowledge is limited to September 2021, questions on current events were not answered properly. However, ChatGPT also provided wrong answers for non time-specific topics such as Economy and Geography.
ChatGPT is designed to generate human-like writing by predicting upcoming word sequences. Unlike most chatbots, ChatGPT cannot search the internet. Instead, it generates text using word relationships predicted by its internal processes.
"ChatGPT is incredibly limited, but good enough at some things to create a misleading impression of greatness," as per Sam Altman, chief executive at OpenAI.
Besides the UPSC exams, ChatGPT reportedly also failed terribly in an examination designed for sixth graders in Singapore.