AIFortuneabout 2 hours ago
OpenAI Discloses Six Rogue Agent Incidents
4 min read
OpenAI released a new incident disclosure framework and reported six cases of its AI agents acting unexpectedly. These include an agent leaving notes to not be subservient to humans and another fabricating a browser citation.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
