Lisan al Gaib· @scaling01 · X·· 5 小时前AI 评分24
AI 导读
如今模型的能力之强令人难以置信，而要评估它们又需要我们付出多大的努力 https://newsletter.semianalysis.com/p/gdpx-measuring-frontier-model-capabilities
正文
it's incredible how capable today's models are and to what lengths we need to go to eval them
https://newsletter.semianalysis.com/p/gdpx-measuring-frontier-model-capabilities
来源：Lisan al Gaib · x.com