When the New Scientist revealed that it had obtained a UK government minister’s ChatGPT prompts through a freedom of information (FOI) request, many in journalism and politics did a double take. Science and technology minister Peter Kyle had apparently asked the AI chatbot to draft a speech, explain complex policy and – more memorably – tell him what podcasts to appear on.
What once seemed like private musings or experimental use of AI is now firmly in the public domain – because it was done on a government device.
It’s a striking example of how FOI laws are being stretched in the age of artificial intelligence. But it also raises a bigger, more uncomfortable question: what else in our digital lives counts as a public record? If AI prompts can be released, should Google searches be next?
