跳到正文
Andrej Karpathy (@karpathy)· @karpathy · X·· 2 小時前AI 評分58
AI 導讀

Claude Fable 5 是同 Mythos 基礎模型加強安全後的升級版,並在多項基準上取得領先成績。

  • - 效能:在軟體工程、知識工作、科學研究與視覺任務上均為 SOTA。
  • - 安全:新增安全機制。
  • - 影響:長且複雜任務中領先幅度更大。
正文

This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward
Fable 5 is state-of-the-art on nearly all tested benchmarks, with exceptional performance in software engineering, knowledge work, scientific research, and vision. The longer and more complex the task, the larger Fable 5’s lead over our other models.

來源:Andrej Karpathy (@karpathy) · x.com