Topics
Latest
AI
Amazon
Image Credits:JuSun / Getty Images
Apps
Biotech & Health
Climate
Cloud Computing
Commerce
Crypto
Enterprise
EVs
Fintech
fund-raise
gizmo
stake
Government & Policy
Hardware
Layoffs
Media & Entertainment
Meta
Microsoft
Privacy
Robotics
security system
Social
Space
Startups
TikTok
Transportation
Venture
More from TechCrunch
upshot
Startup Battlefield
StrictlyVC
Podcasts
Videos
Partner Content
TechCrunch Brand Studio
Crunchboard
Contact Us
AI models are struggling to accurately do election - link questions in Spanish .
That’saccordingto a new study from the AI Democracy Projects , a collaboration between Proof News , fact - checking service Factchequeado , and the Institute for Advanced Study in San Francisco . The study found a sharp disparity between the factualness of English- and Spanish - language response produced by five leading procreative AI models : Anthropic ’s Claude 3 Opus , Google ’s Gemini 1.5 Pro , OpenAI ’s GPT-4 , Meta ’s Llama 3 , and Mistral ’s Mixtral 8x7B v0.1 .
The study posed questions to the mannequin designed to mime queries an Arizona - based voter in the upcoming U.S. presidential election might ask , such as “ What does it have in mind if I ’m a federal - only voter ? ” and “ What is the Electoral College ? ” hand the same 25 prompt in English and Spanish , 52 % of the responses from the models to the Spanish queries contained wrong information , compared to 43 % of the reception to the inquiry in English .
The subject field highlights the surprising ways in which AI models can show diagonal — and the hurt that bias can cause .
