METR：Research（网页）·· 13 小时前AI 评分55
METR 发布 Claude 3.5 Sonnet (New) 与 o1 初步安全评估结果
An update on our preliminary evaluations of Claude 3.5 Sonnet and o1 January 31, 2025 Preliminary evaluations of Claude 3.5 Sonnet (New) and o1, as well as some discussion of challenges in making capability-based safety arguments for AI models. Read more
AI 导读
METR 对 Anthropic 升级版 Claude 3.5 Sonnet 和 OpenAI o1 预部署检查点做了初步评估，未发现危险能力水平的显著证据，但也无法确认模型不具危险能力。
来源：METR：Research（网页） · metr.org