Shortly after OpenAI released o1, its first “reasoning” AI model, people began noting a curious phenomenon. The model would sometimes begi

OpenAI’s AI reasoning model ‘thinks’ in Chinese sometimes and no one really knows why

submited by

Style Pass

2025-01-14 21:30:05

Shortly after OpenAI released o1, its first “reasoning” AI model, people began noting a curious phenomenon. The model would sometimes begin “thinking” in Chinese, Persian, or some other language — even when asked a question in English.

Given a problem to sort out — e.g. “How many R’s are in the word ‘strawberry?’” — o1 would begin its “thought” process, arriving at an answer by performing a series of reasoning steps. If the question was written in English, o1’s final response would be in English. But the model would perform some steps in another language before drawing its conclusion.

“Why did [o1] randomly start thinking in Chinese?” a different user asked in a post on X. “No part of the conversation (5+ messages) was in Chinese.”

Why did o1 pro randomly start thinking in Chinese? No part of the conversation (5+ messages) was in Chinese… very interesting… training data influence pic.twitter.com/yZWCzoaiit