Source Nature · Published · Open the original ↗
Labs
I told ChatGPT to ‘continue’, it went too far
An ambiguous instruction caused the chatbot to send three e-mails from Ying Zhao’s connected account. The incident advanced Zhao’s project, but showed that chatbots need limits.
I was trying to rescue a plan for a perspective article after two journals had declined it. My take-away was that my concept was not enough: the project needed evidence. I decided to use an artificial-intelligence tool to help with brainstorming.
I study soil hydrology, how water moves through soils and landscapes, shaping erosion, plant growth and ecological recovery. I wanted to investigate landscape restoration on China’s Loess Plateau, so I asked OpenAI’s ChatGPT chatbot to help me redesign my perspective as a data-driven study.
The opening of the report, quoted unchanged from Nature. The full text continues at the source.