Ethan Mollick 谈开放权重模型的网络安全风险
中文全文 · AI 翻译
先不谈 Anthropic 发表这项研究的动机，毫无疑问，开放权重模型很快也会带来闭源模型已经展现出的同类安全威胁，只是没有相应防护措施。我们离这一步已经很近了。最好据此提前做好规划。
对照原文
Leaving aside Anthropic's incentives for publishing this research, there is no doubt that open weights models will soon create the same security threats that closed source models have been demonstrating, except without guardrails. We are close. Probably good to plan accordingly. https://t.co/aZ73iZyFXp
https://t.co/ldgND9KkGu