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 is getting less “woke” because of a new political…

AI Risks October 13, 2025 · KnowTechie

ChatGPT is getting less “woke” because of a new political bias test - KnowTechie

Four models, GPT-4o, OpenAI o3, and the newer GPT-5 pair were put through the wringer. Then, another AI model graded their answers using a rubric that ...

Read the original at KnowTechie ↗

Topics
Bias & Fairness
Mentions
OpenAIGPTChatGPT
Tracked via
“AI Bias”

Related articles

  • ChatGPT is getting smarter, but its hallucinations are spiraling - MSN AI Hallucinations · May 08, 2025
  • ChatGPT is getting smarter, but its hallucinations are spiraling - TechRadar AI Hallucinations · May 07, 2025
  • Newest generation of GPT models show major drop in political bias , OpenAI says AI Risks · Oct 10, 2025
  • OpenAI's GPT-5: Cutting Political Bias or Curtailing ChatGPT's Agreeableness? | AI News AI Risks · Oct 19, 2025
  • Anthropic's bot bias test shows Grok and Gemini are more "evenhanded" AI Risks · Nov 15, 2025
  • OPINION: Just Be You - The New Political AI Use Cases · Apr 25, 2025

Shares players with

  • Outsized Hype About ChatGPT GPT-5 Being Totally Honest AI Is Basically A Big Fib - Forbes
  • 'GPT-5 be trusted at all now': ChatGPT user slams AI over broken rules, hallucinations
  • ChatGPT Gets GPT-5.3 Instant Update With Less 'Cringe,' Fewer Hallucinations
  • OpenAI starts rolling out GPT-5.3 Instant in ChatGPT as default everyday model
  • OpenAI releases GPT‑5.5 Instant as new default AI model on ChatGPT - MSN
  • ChatGPT-6 Explained: How AI Evolved From GPT-3.5 to GPT-4o - Daily Sun

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