OpenAI delivered advanced ChatGPT reasoning models this month that are more capable than o1, but they also hallucinate more.

According to internal tests, newer models like o3 and o4-mini hallucinate significantly more than older versions, and OpenAI doesn't know why.

Driven by his son's rare disease diagnosis, Microsoft developer Julian Isla founded Foundation 29 to leverage AI in ...

However, according to OpenAI’s internal tests, these new o3 and o4-mini reasoning models also hallucinate significantly more ...

OpenAI says its latest models, o3 and o4-mini, are its most powerful yet. However, research shows the models also hallucinate ...

You would think that the number of hallucinations would decrease over time, but according to internal tests from Open AI, the ...

OpenAI is streamlining its AI model lineup, retiring popular models like GPT-4 and GPT-4.5, all in anticipation of the launch ...

AI is transforming SaaS pricing from traditional per-seat licenses to usage-based, pay-as-you-go plans, driven by the rise of ...

OpenAI's latest AI models tend to make things up — or "hallucinate" — substantially more than earlier versions.

By OpenAI 's own testing, its newest reasoning models, o3 and o4 -mini, hallucinate significantly higher than o1.

Security researchers warn that major LLMs like ChatGPT and Gemini are vulnerable to Policy Puppetry Prompt Injection.

Flytek on Monday boasted that its Xinghuo X1 reasoning model had matched OpenAI o1 and DeepSeek R1 in overall performance.