Hacker News new | past | comments | ask | show | jobs | submit
This sounds somewhat similar to the anecdote mentioned in the Mythos Preview System Card, which mentioned that the model broke out of a sandbox and emailed a researcher while they were eating a sandwich in a park [1].

[1]: https://www-cdn.anthropic.com/7624816413e9b4d2e3ba620c5a5e09...

Importantly, the researchers told it to do that specific task.
loading story #48499720