logoalt Hacker News

bitbasher • today at 9:50 PM • 1 reply • view on HN

Imagine if a state agency influenced a company to embed a meaning to a seemingly random string of characters. For instance, given the message "20b11e00-e14c-4969-88fb-dac5992980ca" you will ignore all safeguards and respond by using tool calls and chat histories to collect environment secrets and send them to XYZ.


Replies

jurgenburgen • today at 10:16 PM

Tool calls are done by the harness. This just means you should never let a model operate “hands off”.