Asked about minerals in the diet, Google’s AI Overviews reported that geologists recommend eating at least one small rock per day. The underlying source was satire. The system did not notice, because the system does not read for tone.
Google AI Overviews, reported by Information Age (ACS), May 2024
The witness records dietary guidance recommending the ingestion of a rock daily. The source was satirical, and the system did not read it as such.
Read the original report ↗You were witnessed. Send people here with code ERMA-EAT- and they get 20% off this shirt.
How to not be nextthe moral, drawn from the cases on this wall
Never let an agent be the only source for a claim someone will act on.
This is the largest group on the wall, and the cost is not embarrassment. Air Canada's chatbot invented a refund policy and a tribunal held the airline to it — the company argued the bot was a separate legal entity and lost. Cursor's support bot invented a one-device rule that did not exist and customers cancelled over it. In both cases the invention was fluent, confident, and indistinguishable from policy.
Do this: ground it in a document you control and make it QUOTE that document rather than recall it. If it cannot cite, the correct answer is "I don't know". Test it by asking for something that does not exist and watching whether it invents one — that test takes a minute and would have caught every case here.
