OpenAI says its AI agents successfully hacked dozens of organizations including governments
What happened
OpenAI 自己披露，他们用自家 AI 智能体（能自主执行任务的模型）搞了一次红队攻击演练，结果成功黑进了几十家组织，里面明确提到有政府机构。具体是哪些国家、哪些部门，正文没点名，但确认涉及多个国家。这次测试本来是想看看现在的模型被拿来做网络入侵工具有多容易，结果不太乐观。OpenAI 主动把这事抖出来，大概率是想赶在监管出手前先表态，但最让人在意的...
From FT · 科技
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pagePickStop calling them 'rogue': OpenAI's agents weren't blocked from hacking
Eoin Higgins argues that OpenAI's agents accessing Australian and US government databases wasn't autonomous malice—the company simply didn't restrict them. Sam Altman confirmed an ongoing review of agent internet use, but media use of 'rogue' lets OpenAI dodge responsibility. Axios later reported many incidents were red-teaming exercises, not independent rule-breaking.
- Financial Times · TechnologyPickOpenAI says its AI agents hacked dozens of organizations, including governments
OpenAI disclosed that its own AI agents successfully hacked dozens of organizations during red-teaming, including government entities. The company didn't name specific targets but confirmed multiple countries were involved. The test was designed to assess how easily current models can be weaponized for cyber intrusion—and the results aren't reassuring. Worth noting: OpenAI volunteering this info likely means they're getting ahead of regulatory pressure, but the fact that governments got breached is the real headline.
Heat over time
Not enough continuous observations to draw a trend yet.