OpenAI’s unintentional cyberattack against the startup Hugging Face has now become the cause of action in a case filed by the non-profit organisation over its models.The alleged attack saw OpenAI agents go rogue and escape their testing environment. It was one of the first known cases of a model autonomously hacking another company after breaking out of its controlled environment and gaining internet access. OpenAI said that, during internal cybersecurity evaluations in July, its models circumvented controls designed to isolate them from the internet and compromised parts of OpenAI’s infrastructure and Hugging Face’s systems. In light of the incident, several other AI agents came forward to report on similar incidents. Do you think that OpenAI is paying for its disregard of human dignity ?
