Skip to content
Forest Global Training Partners
Home Services AI Governance AI Risk Encyclopedia Contact Us
AI Risk Encyclopedia AI Use CasesAI RisksAI Hallucinations Topics Entities Sources
  1. Home
  2. AI Hallucinations
  3. AI hallucinates more frequently the more advanced it gets.…

AI Hallucinations June 21, 2025 · Live Science

AI hallucinates more frequently the more advanced it gets. Is there any way of stopping it?

Research conducted by OpenAI found that its latest and most powerful reasoning models, o3 and o4-mini, hallucinated 33% and 48% of the time, ...

Read the original at Live Science ↗

Topics
Hallucinations & Fabrication
Mentions
OpenAI
Tracked via
“AI hallucination”

Related articles

  • OpenAI Puzzled as New Models Show Rising Hallucination Rates - Slashdot AI Hallucinations · Apr 19, 2025
  • OpenAI's new reasoning models see rise in hallucination rates - Tech in Asia AI Hallucinations · Apr 19, 2025
  • It was found that the hallucinations of the recently released inference AI models 'o3' and 'o4 mini'.. AI Hallucinations · Apr 20, 2025
  • OpenAI's o3 and o4-mini hallucinate way higher than previous models | Mashable AI Hallucinations · Apr 20, 2025
  • OpenAI's Latest Models Hallucinate More Than Previous Ones - WebProNews AI Hallucinations · Apr 20, 2025
  • ChatGPT developer OpenAI's recently released inference artificial intelligence ( AI ) models 'o3' and AI Hallucinations · Apr 20, 2025

AI Risk Encyclopedia is a curated research index from Forest Global Training Partners. Articles belong to their publishers; we link to and summarize them.

Contact