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. No, you can't get your AI to 'admit' to being sexist, but…

AI Risks November 29, 2025 · TechCrunch

No, you can't get your AI to 'admit' to being sexist, but it probably is | TechCrunch

Though LLMs might not use explicitly biased language, they may infer your demographic data and display implicit biases , researchers say.

Read the original at TechCrunch ↗

Topics
Bias & FairnessChatbots & LLMs
Tracked via
“AI Bias”

Related articles

  • British judges are now routinely using AI . Not all of them admit it - The Telegraph AI Hallucinations · Dec 13, 2025
  • AI won't admit it, but it probably is biased - KnowTechie AI Risks · Dec 01, 2025
  • Most Workers Use AI , But Those Who Admit It Are Facing Workplace Bias - Allwork.Space AI Risks · Jun 12, 2026
  • Using a simple 'cupcake' trick makes AI admit when it's guessing, helping you spot ... AI Hallucinations · Mar 17, 2026
  • Algorithms are also sexist: this is how they amplify discrimination against women AI Risks · Mar 08, 2026
  • Tackling hallucinations: MIT spinout teaches AI to admit when it's clueless - AI News AI Risks · Jun 05, 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