Meta的代码生成模型经评估无新增前沿风险，已开源。
Code World Model Preparedness Report
- 在潜在高危领域测试代码模型能力
- 未发现超出现有AI生态的风险
- 适合关注代码生成与安全评估的研究者
本报告记录了Meta开发的代码世界模型（Code World Model, CWM）的准备就绪评估。我们在前沿人工智能框架识别出可能带来灾难性风险的领域进行了发布前测试，并评估了该模型的不对齐倾向。评估结果表明，CWM不存在超出当前人工智能生态系统范围的前沿风险。因此，我们决定以开放权重形式发布该模型。
原文摘要 · Abstract (English)
This report documents the preparedness assessment of Code World Model (CWM), a model for code generation and reasoning about code from Meta. We conducted pre-release testing across domains identified in our Frontier AI Framework as potentially presenting catastrophic risks, and also evaluated the model's misaligned propensities. Our assessment found that CWM does not pose additional frontier risks beyond those present in the current AI ecosystem. We therefore release it as an open-weight model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。