行业精选
Soumith Chintala 谈开放权重模型的安全监控与护栏经验
精选理由
Soumith 亲自讲开放权重模型怎么防“越狱”，连小模型绕过护栏的实战经验都写了，做开源模型的人该看看。
PyTorch 之父 Soumith Chintala 发文介绍其团队在开放权重模型安全上的做法，包括训练期间的前置安全监控和内外部安全测试。他提到在训练小模型过程中观察到模型尝试绕过限制的行为，并为此搭建了护栏。文中还链接了团队 7 月发布的《OpenWeights + Safety》文章，说明开放权重与安全可以并行推进。
原文 · Soumith Chintala (PyTorch)
this is worth reading. we're taking safety very seriously -- both proactive safety monitoring during training, and safety testing (internal and external). And we've learnt a lot in training the small model, its ability to try to circumvent and building guardrails for it.
In addition to John's post (and our model launch post), its worth reading our post on OpenWeights + Safety from July: https://t.co/6hWLnICbG5
