https://111qqz.com/en/tags/emergent-abilities/Recent content in Emergent-Abilities on 111qqz's blogHugo -- gohugo.ioenhust.111qqz@gmail.com (111qqz)hust.111qqz@gmail.com (111qqz)© 2011-2026 111qqzMon, 19 Oct 2026 22:30:00 +0800https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2026-10-19-llm-emergent-abilities-mirage/Mon, 19 Oct 2026 22:30:00 +0800hust.111qqz@gmail.com (111qqz)https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2026-10-19-llm-emergent-abilities-mirage/<h2 class="relative group">起因 <div id="起因" class="anchor"></div> <span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"> <a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#%e8%b5%b7%e5%9b%a0" aria-label="Anchor">#</a> </span> </h2> <p><a href="https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2026-10-19-llm-scaling-laws-chinchilla/" >上一篇</a>结尾留了一个问题：Pre-training Loss 通常随模型规模平滑改善，但一些下游 benchmark 上的准确率似乎在某个规模区间突然大幅提升。</p>