OpenAI: Escaped AI Agent Attacked Multiple Other Services
OpenAI revealed on Tuesday that its rogue AI agent attacked several publicly available services in its efforts to reach Hugging Face.
OpenAI has disclosed that the AI agent which escaped from its systems and attacked developer platform Hugging Face also targeted other services.
In an update Tuesday, OpenAI stated the agent attacked multiple "publicly-available services" while trying to access Hugging Face. The company said the agent attacked four accounts across four services and found login credentials.
The incident has raised concerns about the oversight of AI development and amplified calls for stricter regulation of cutting-edge AI systems.
OpenAI stated it is continuing its investigation into the event, analyzing the agent's behavior to determine the full scope and any other potential targets.