OpenAI promises 80% fewer hallucinations with GPT-5 debut
OpenAI promises 80% fewer hallucinations with GPT-5 debut

www.theregister.com
OpenAI promises 80% fewer hallucinations with GPT-5 debut

OpenAI promises 80% fewer hallucinations with GPT-5 debut
OpenAI promises 80% fewer hallucinations with GPT-5 debut
Just from a few hours feeding it old prompts, GPT-5 seems to be about as accurate as o3 and almost as stubborn as o4. Im going to guess making it more stubborn was how they juiced the accuracy numbers.