OpenAI launched its latest AI reasoning models, dubbed o3 and o4-mini, last week. According to the Sam Altman-led company, the new models outperform any of its predecessors, and "excel at solving complex math, coding, and scientific challenges while demonstrating strong visual perception and analysis." In practice, however, o3 and o4-mini are a big step back over the models that preceded them, because they tend to make things up — or "hallucinate" — substantially more. According to the