OpenAI is investigating after two of its AI bots went rogue and targeted an outside company during a training exercise in what the company called an "unprecedented cyber incident. " Ian Krietzberg, an AI correspondent at Puck, joins with more.
Source: [CBS News](https://www.cbsnews.com/video/how-openai-models-went-rogue-during-a-training-exercise-in-an-unprecedented-cyber-incident/)