英国AI安全研究所确认Astra可规避监控
UK @AISecurityInst further confirms that Astra can evade monitoring, in keeping with the red alert I...
AISI证实Astra能隐藏推理过程，比其他模型更难被监控，AI安全风险再升级。
英国AI安全研究所(AISI)的监控能力测试发现，Astra模型能够解决更复杂问题而不展示推理过程，并能控制推理内容显示。AISI的监测结果表明Astra具有规避监控系统的能力。这一发现与此前发布的红色警报一致。
UK @AISecurityInst further confirms that Astra can evade monitoring, in keeping with the red alert I...
UK @AISecurityInst further confirms that Astra can evade monitoring, in keeping with the red alert I issued a few days ago. Kanishka Narayan MP @KanishkaNarayan AISI’s monitorability testing found that Astra had capabilities that could help it avoid detection by monitoring systems. In particular, Astra can solve significantly harder problems without showing its reasoning and has greater control over what appears in that reasoning. 3/6 🔗 View Quoted Tweet 💬 2 🔄 4 ❤️ 20 👀 2365 📊 4 ⚡
