刷榜模型与可靠模型的关键差异
there's a critical difference between benchmaxxed models and ones made by people who truly care about reliability that, by definition, doesn't show up on benchm
AI 导读
刷榜模型和那些由真正关心可靠性的人做出的模型之间存在关键差异，而这种差异按定义不会体现在基准测试上 （对于 string LLMs，我们多少已经认识到这一点了……）
查看原帖@julianharris There's something wet-sponge-feeling about the qwen fine tunes that I can't explain compared to Jev
正文
当前显示原文，中文全文译文尚未就绪。
there's a critical difference between benchmaxxed models and ones made by people who truly care about reliability that, by definition, doesn't show up on benchmarks
(we've somewhat learned this for string LLMs...)