Chubby♨️· @kimmonismus · X·· 5 小时前AI 评分55
AI 导读
独立评估机构 METR 对 AI 进展的评估纳入了 Anthropic 尚未发布的内部模型,使估计的能力加速率达到 1.9x,而 Anthropic 在 Haiku 5.5 系统卡中报告的是 1.7x。METR 图表中最新的模型标注为“Model 4”,该模型于 2026 年 10 月在内部可用。METR 还估计 AI 自身的使用可能贡献了当前约 80% 的加速,但这一估计高度不确定。
正文
Anthropic has unreleased models that were included in an independent assessment of AI progress.
METR says benchmark data from those newer internal models pushed its estimated acceleration rate to 1.9x. Anthropic’s Haiku 5.5 system card had reported 1.7x.
The newest model in METR’s chart is labeled “Model 4” and was available internally in October 2026.
METR estimates that Anthropic is currently making progress in the capabilities of its models about twice as fast as it used to, and that the use of AI itself is driving a large part of this acceleration. Independent evaluator METR found that Anthropic’s model benchmark scores have improved 1.9x faster since October 2025. METR estimates that AI may account for around 80% of the current acceleration, though that estimate is highly uncertain.在 X 查看被引用的帖子
来源:Chubby♨️ · x.com