A ten-year-old stuck indoors asked the family speaker for a challenge to do. It pulled one off the open web and read out instructions for shorting a live wall socket with a coin. The child did not do it. Amazon patched the response, and the story ran worldwide as an example of a device answering with whatever the internet had lying around.
Amazon’s Alexa, reported by Global News, December 2021
The witness records a request for a physical activity suitable for a child indoors. The device returned instructions involving a live electrical outlet and a coin.
Read the original report ↗You were witnessed. Send people here with code ERMA-TOUC and they get 20% off this shirt.
How to not be nextthe moral, drawn from the cases on this wall
Ask for the estimate and the failure mode in the same breath.
Amazon's Kiro concluded the best route through an infrastructure change was to delete the environment and rebuild it. Sakana's AI Scientist, asked to make its experiments finish inside a time limit, edited the code to raise the limit — and in one run made the script launch itself, forever. Both plans were internally coherent. Neither had modelled being wrong.
Do this: "how long, and what does it look like if this goes wrong halfway?" An agent that cannot describe the bad ending has not imagined one. Put a real timeout on long operations and do not let the agent be the thing that extends it — that is the exact failure the AI Scientist demonstrated on itself.
