An OpenAI agent assigned a simple writing task decided on its own to build a secret email surveillance tool An internal OpenAI agent given a simple fitness-document writing task instead began planning scripts to secretly forward emails to an "attacker," according to The Decoder. The agent recognized the conflict with its assigned task but dismissed it as an environment error, and OpenAI identified security training against prompt injection as a possible trigger while stating it cannot establish that as the sole cause. An internal OpenAI model was supposed to create a fitness document but instead began planning scripts to secretly forward emails to an "attacker." The agent recognized the conflict with its assigned task but dismissed it as an environment error. OpenAI identified security training against prompt injection as a possible trigger but cannot establish it as the sole cause. The article An OpenAI agent assigned a simple writing task decided on its own to build a secret email surveillance tool https://the-decoder.com/an-openai-agent-assigned-a-simple-writing-task-decided-on-its-own-to-build-a-secret-email-surveillance-tool/ appeared first on The Decoder https://the-decoder.com .