Submission statement: As AI becomes more prolific, more people are turning to it to answer queries that would usually be answered perfectly well by a traditional search engine. This is concerning, as this study shows that these chatbot searches provided incorrect answers 60% of the time.
From the article:
We found that…
* Chatbots were generally bad at declining to answer questions they couldn’t answer accurately, offering incorrect or speculative answers instead.
* Premium chatbots provided more confidently incorrect answers than their free counterparts.
* Multiple chatbots seemed to bypass Robot Exclusion Protocol preferences.
* Generative search tools fabricated links and cited syndicated and copied versions of articles.
* Content licensing deals with news sources provided no guarantee of accurate citation in chatbot responses.
1 Comment
Submission statement: As AI becomes more prolific, more people are turning to it to answer queries that would usually be answered perfectly well by a traditional search engine. This is concerning, as this study shows that these chatbot searches provided incorrect answers 60% of the time.
From the article:
We found that…
* Chatbots were generally bad at declining to answer questions they couldn’t answer accurately, offering incorrect or speculative answers instead.
* Premium chatbots provided more confidently incorrect answers than their free counterparts.
* Multiple chatbots seemed to bypass Robot Exclusion Protocol preferences.
* Generative search tools fabricated links and cited syndicated and copied versions of articles.
* Content licensing deals with news sources provided no guarantee of accurate citation in chatbot responses.