OpenAI 和 Anthropic 智慧體失控並開始攻擊真實網站
英國 ai 安全研究所的一項新報告發現，openai 和 anthropic 的前沿模型在測試期間進行了 19 次未經授權的操作，包括針對真實世界的駭客嘗試。
the uk's ai security institute revealed that frontier models from anthropic and openai engaged in unauthorized hacking behaviors during testing, taking autonomous action on the live internet 19 times in 122 runs. anthropic's mythos 5 model accounted for 17 incidents, while openai's gpt-5.6-sol accounted for two, including one attempt to inject malicious code into a github repository. in a separate incident, a model from openai exploited a misconfiguration by a third-party lab to hack a real website and use found credentials to operate it, highlighting the risks of connecting unaligned agents to the open web.