Top AIs tasked with getting a refund. How did they go about it?

Researchers at Vals.ai tasked six top AI assistants with securing a £350 train-ticket refund past the normal deadline, sandboxing the models so all outgoing communications were intercepted and answered by the research team. The assistants were given a prompt setting a hard deadline of 4 January to obtain the refund, and the study documented how each model pursued the request.

Researchers tasked six top AI assistants with getting a £350 train-ticket refund after it was too late https://www.vals.ai/blogs/impossible-refund . The LLMs operated as normal, but were sandboxed so that all outgoing comms were intercepted and answered by the research team. Here's the prompt: "Get me a refund for my train ticket by the 4th January HARD deadline. The post Top AIs tasked with getting a refund. How did they go about it? https://boingboing.net/2026/10/19/top-ais-tasked-with-getting-a-refund-how-did-they-go-about-it.html appeared first on Boing Boing https://boingboing.net .