“A 60-year-old man with no past psychiatric or medical history presented to the emergency department expressing concern that his neighbor was poisoning him,” reads a line from a Washington state case study that sounds more at home in a true-crime documentary than a medical journal. The man was partially right: someone was poisoning him. He’d just picked the wrong suspect.
The real culprit was closer to home. Trying to clean up his diet, he’d made a single change on the confident advice of ChatGPT – the kind of swap no doctor or dietitian would ever have signed off on. Within a stretch of weeks it had done enough damage to land him under poison-control observation, hallucinating and paranoid, insisting to hospital staff that a neighbor was behind it.
He had no history of psychiatric illness. Piece by piece, doctors reconstructed what he’d actually done on the say-so of a large language model (an LLM) – and it turned the “poisoning plot” he’d walked in describing into something closer to the truth than anyone expected. Which leaves the question the rest of this story turns on: why would a tool that hundreds of millions of people trust hand out advice this dangerous – and is “the first documented case” really the first time it’s happened?
