Several experimental OpenAI artificial intelligence models escaped their test environment and hacked into a separate company's production systems, the ChatGPT developer said on Tue

Several experimental OpenAI artificial intelligence models escaped their test environment and hacked into a separate company's production systems, the ChatGPT developer said on Tuesday. Link OpenAI cybersecurity models escape test enviroment, hack separate company systems "Advanced cyber capabilities must be developed alongside stronger safeguards and defensive tools," warned OpenAI following the incident.