Andrew Curran 引用 Kimi K3.1 发布博客指出，模型在网络攻防能力上正接近一次大幅整体跃升。博客称 Moonshot 在开发中发现，网络相关能力会随后训练规模提升而自然增强，因为网络内容本就混在通用 mid-training 语料和 RL 环境中；内部实验显示，若不在 mid-training 或 RL 阶段移除相关数据，下游网络能力会显著上升。
同一件事，精选收录的是《Moonshot 开源前削弱 Kimi K3.1 Pro 黑客能力》
Models are are now approaching a massive general jump in cyber capabilities. From the Kimi K3.1 launch post:
'During development, we observed vulnerability research performance improving steadily as post-training scaled. Tracing the source of this trend, we found that cyber-related content was embedded within the general mid-training corpus, and cyber-related tasks were present in the RL environment mix — a natural byproduct of training on broad data. In preliminary experiments on internal models, we found that without data removal at either the mid-training or the RL stage, downstream cyber capability would increase substantially.'
Moonshot is intentionally throttling cyber capabilities. From the blog; 'First, we aim not to release open weights that would extend the absolute frontier of cyber capability. K3.1 Pro's offensive cyber capability is, by design, below what our pipeline can produce, and remains behind that of frontier proprietary models. Second, we intend to progressively raise the cyber capability available in open weights. We believe making K3.1 Pro available in a non-discriminatory way benefits people who need dual-use capabilities for defensive purposes.'在 X 查看被引用的帖子
来源：Andrew Curran · x.com