Study finds AI shopping assistants wrong 86% of the time on prices and specs
A study by Product.ai tested free and paid versions of four AI models—ChatGPT, Gemini, Perplexity, and Claude—on 220 shopping questions. The models provided incorrect or conflicting information in 86% of responses, with comparison questions wrong 97% of the time. Errors included outdated product listings, contradictory prices, and exaggerated specifications. For high-cost items like laptops,…
Key points
- Product.ai tested four AI models on 220 shopping questions, finding 86% of answers wrong or conflicting
- Comparison questions were wrong 97% of the time, with median price errors of $300 for high-cost items
- 10% of incorrect responses had errors of $500 or more, per the study’s researchers
Study: AI Shopping Assistants Are Wrong 86% of the Time
tech.co · 25 September 2026
Loading the full article…
This text was published by tech.co and written by Conor Cawley. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Marketing & Small Business
All →- Ryo shows how to use Gemini, ChatGPT, and Claude for A 20‑minute side hustle · 6 src
- Anthropic course teaches prompt formula to improve AI response quality · 2 src
- AI beginner separates photo facts from inferences in ChatGPT tests · 1 src
- Mechanic-turned-podcaster warns against blindly copying AI resume outputs · 1 src
- AI agents amplify bad audience data, warns Skydeo’s Mallory Gray · 1 src
Comments
via GitHub Discussions