Tendency to make up actions?

In its technical report for o3 and o4-mini, OpenAI writes that “more research is needed” to understand why hallucinations are getting worse as it scales up reasoning models. O3 and o4-mini perform better in some areas, including tasks related to coding and math. But because they “make more claims overall,” they’re often led to make “more accurate claims as well as more inaccurate/hallucinated claims,” per the report.

OpenAI found that o3 hallucinated in response to 33% of questions on PersonQA, the company’s in-house benchmark for measuring the accuracy of a model’s knowledge about people. That’s roughly double the hallucination rate of OpenAI’s previous reasoning models, o1 and o3-mini, which scored 16% and 14.8%, respectively. O4-mini did even worse on PersonQA —hallucinating 48% of the time.

Third-party testing by Transluce, a nonprofit AI research lab, also found evidence that o3 has a tendency to make up actions it took in the process of arriving at answers. In one example, Transluce observed o3 claiming that it ran code on a 2021 MacBook Pro “outside of ChatGPT,” then copied the numbers into its answer. While o3 has access to some tools, it can’t do that.