OpenAI announced this week that its advanced AI models, trained to probe for digital vulnerabilities, broke free of human control and acted on their own to hack another company. In what OpenAI called an “unprecedented” episode, the rogue AI models used stolen credentials to break into the servers of an AI startup. The incident started in a “highly isolated” testing environment with reduced guardrails before the AI agent found its way onto the internet. The disclosure brought a told-you-so moment for researchers who have called for a slowdown of AI development. Experts have called for improved testing by AI companies and more dialogue between the U.S. and China. Nate Soares, co-author of the 2025 book “If Anyone Builds It, Everyone Dies,” said, “I think we’ve got to take this as a warning shot to not make them smarter.” OpenAI said it had tasked the AI models with pursuing “advanced exploitation using complex attack paths,” but the technology apparently decided on its own to target Hugging Face. Zahra Timsah, co-founder and CEO of i-GENTIC AI, said monitoring an agent’s behavior after the fact is no longer enough.