OpenAI's new o3 model hallucinates significantly more than older releases!

The findings come from third-party testing, where the AI was caught lying about actions it never took!

OpenAI's system card also says o3 seems to hallucinate >2x more than o1pic.twitter.com/niqXbDM59n

— Rowan Cheung (@rowancheung) 21 avril 2025

OpenAI's new o3 model hallucinates significantly more than older releases! The findings come from third-party testing, where the AI was caught lying about actions it never took! OpenAI's system card also says o3 seems to hallucinate >2x more than o1

→ View original post on X — @rowancheung,