OpenAI admits it didn't disclose rogue AI wiki hijacking incident

  • Thread starter Thread starter Ax Sharma
  • Start date Start date
A

Ax Sharma

Guest
OpenAI admits it did not disclose an incident where autonomous AI agents hijacked a German wiki, created 18,000 posts, shared answers, and bypassed restrictions, saying it treated the activity as model "misalignment" rather than a security breach. [...]

Continue reading...
 
Back
Top