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. OpenAI's most capable models hallucinate more than earlier…

AI Hallucinations April 22, 2025 · ZDNET

OpenAI's most capable models hallucinate more than earlier ones - ZDNET

In the system card, a report that accompanies each new AI model, and published with the release last week, OpenAI reported that o4-mini is less ...

Read the original at ZDNET ↗

Topics
Hallucinations & FabricationMedia & Creative Work
Mentions
OpenAI
Tracked via
“AI hallucination”

Related articles

  • OpenAI's Latest Models Hallucinate More Than Previous Ones - WebProNews AI Hallucinations · Apr 20, 2025
  • SafetyKit's blueprint for scaling risk agents with OpenAI's most capable models AI Risks · Sep 10, 2025
  • "Nonsensical Benchmark Hacking": Microsoft No Longer Believes OpenAI Is Capable of ... - Futurism AI Use Cases · Jun 27, 2025
  • Why language models hallucinate | OpenAI AI Hallucinations · Sep 05, 2025
  • OpenAI proposes a second neural net to catch ChatGPT's code mistakes | ZDNET AI Hallucinations · Jul 03, 2024
  • Why AI models hallucinate | Here & Now - WBUR AI Hallucinations · Sep 08, 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