Why AI chatbots lie to us.
expert_opinion · Level V
Where this comes from
- Record sourced from PubMed, PMID 40705883.
- Also identified by DOI 10.1126/science.aea3922.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
A few weeks ago, a colleague of mine needed to collect and format some data from a website, and he asked the latest version of Anthropic's generative AI system, Claude, for help. Claude cheerfully agreed to perform the task, generated a computer program to download the data, and handed over perfectly formatted results. The only problem? My colleague immediately noticed that the data Claude delivered was entirely fabricated.