Drooid Logo
Back to today’s briefing

Story perspectives

Study: Over 60% of AI Search Results Are Wrong

4/1/2026

43 7 Full Breakdown

1 of 1

Story summary
  • A Columbia Journalism Review study finds over 60% of AI search results are incorrect.
  • Researchers tested eight AI models, including OpenAI's ChatGPT and Google's Gemini.
  • Perplexity was the best performer, with 37% of its answers incorrect.
  • Elon Musk's Grok 3 had a 94% error rate, illustrating reliability concerns.
  • Tech companies continue to promote AI-driven search models despite these findings.