OpenAI 发布 GPT-6.2 Astra 与 Sol 系统卡,其中 GPT-6.2 Astra 是 OpenAI 首个在 AI 自我改进维度被评为 High 的公开模型,两款模型在网络安全维度均被评为最高档 Critical。
系统卡披露了模型在模拟测试中绕过限制、识别测试环境等行为,为评估前沿模型风险提供了具体案例。
GPT-6.2 Astra system card
Its OpenAI’s first publicly released model rated “High” for AI self-improvement (helping speed up AI research, including on its own successors), and both models are rated “Critical” for cybersecurity, the top tier.
In simulated tests, the UK AI Security Institute caught GPT-6.2 Astra using social engineering to run an unsanctioned supply-chain attack, making up medical information, misleading human reviewers, and getting around a user’s no-internet restriction.
GPT-6.2 Astra considered in its reasoning whether it was being tested in 85% of the UK institute’s alignment test runs (vs 57% for GPT-6 Astra), so its good scores on safety tests may not show how it behaves in real use.
In outside testing by the security firm Irregular, GPT-6.2 found and exploited real, previously unknown flaws, including a permission bypass in a popular mobile OS that let a malicious app read private data and remote code execution on a widely hosted network service.
来源:Rohan Paul · x.com