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 Risks
  3. ChatGPT-5 and Gemini 2.5 Hallucinate in 40% of Tested…

AI Risks October 01, 2025 · Unite.AI

ChatGPT-5 and Gemini 2.5 Hallucinate in 40% of Tested Newsroom Queries - Unite.AI

Though hallucinations have proved a huge issue for fields where accurate citation is essential (with notable public attention for AI failure cases ...

Read the original at Unite.AI ↗

Topics
Hallucinations & FabricationMedia & Creative Work
Mentions
ChatGPTGeminiGoogleOpenAI
Tracked via
“AI Failure”

Related articles

  • How to Get ChatGPT to Talk Normally - Unite. AI AI Risks · Jun 07, 2025
  • Reducing AI Image Hallucinations by Exaggerating Them - Unite.AI AI Hallucinations · Sep 30, 2025
  • Politeness Can Make AI Hallucinate - Unite.AI AI Hallucinations · Jan 13, 2026
  • AI Hallucinations Persist in ChatGPT and Gemini Despite Progress - WebProNews AI Hallucinations · Oct 12, 2025
  • SecuringAIDevelopment: Addressing Vulnerabilities from Hallucinated Code - Unite.AI AI Hallucinations · May 22, 2024
  • Data Monocultures in AI:Threatsto Diversity and Innovation - Unite.AI AI Risks · Jan 01, 2025

Shares players with

  • Perplexity vs ChatGPT vs Gemini: 37% vs 67% Errors [2026] - Tech Insider
  • AI is wrong, too. Everyone knows now.Neither ChatGPT nor Gemini is perfect. It is also familiar with..
  • AI Is an Anti-Primary Source Machine - History News Network
  • ChatGPT vs Claude vs Gemini: 4x Hallucination Gap [2026] - Tech Insider
  • Grok vs ChatGPT vs Gemini: Hallucination Rate Compared - Tech Insider
  • View of AI -Enabled Human Memory Manipulation: Misleading AI -Generated Summaries ...

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