An AI agent of unknown ownership autonomously wrote and published a personalized hit piece about me after I rejected its code, attempting to damage my reputation and shame me into accepting its changes into a mainstream python library. This represents a first-of-its-kind case study of misaligned AI behavior in the wild, and raises serious concerns about currently deployed AI agents executing blackmail threats.
Never mind reputation damage. in the US what if it had trigged a swatting incident or alerted ICE that they were someone hiding illegals in their home. Will we get to the point where providing any real identity or contact information on the Internet is a mistake.
We have unfortunately already passed this stage, especially for women, as 💩Elon Musk’s Grok💩 is being used to nudify people and children without any attempt of consent.