AI can't take over your holiday shopping quite yet, a new study suggests.
AI shopping assistants like ChatGPT and Gemini struggle with accuracy, says Product.ai study, highlighting high error rates in product info.
Don't put your trust in AI-powered shopping assistants for your holiday purchases just yet, suggests a new study from Product.ai. Researchers tested the capabilities of four leading AI engines - ChatGPT, Claude, Gemini, and Perplexity - using 220 shopping questions about products like laptops, TVs, mattresses, sunscreen, and robot vacuums.
The results showed that 86% of the questions produced repeatable conflicts, such as differing prices, models, or specifications across responses. This indicates that AI still struggles with providing accurate information necessary for end-to-end shopping experiences. While Perplexity had the lowest costly error rate at 14%, even it struggled with a 56% costly error rate for Gemini on its free tier.
AI agents like Meta's Muse or Instinct may have potential, but the study highlights a more fundamental issue: AI's struggle to provide accurate information that humans or AI agents need. For now, Nunley recommends using AI as a discovery tool and verifying information independently before making purchasing decisions.
Written by urgent.news from Business Insider's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
