OpenAI truly does not want you to know what its latest AI model is “thinking.” Since the company launched its “Strawberry” AI model family last week, touting so-called reasoning abilities with o1-preview and o1-mini, OpenAI has been sending out warning emails and threats of bans to any user who tries to probe how the model works.

However, if you try to induce hallucinations in OpenAI's advanced o1 reasoning models, you may lose access to the model altogether. OpenAI unveiled its o1 models last week, which were trained to "think before they speak" and,

OpenAI's new o1 model, designed with "enhanced reasoning," hides its full thought process from users, and gives policy warnings for asking about it.