跳到正文
𝕏 Rohan Paul(x.com)·· 5 天前品質評分50
重點導讀

AI 助理的提示詞和工具由一套程式碼控制;換了模型或測試工作後,原本改好的程式可能反而表現變差,而且看不出每次修改是為瞭解決什麼問題。

  • Google 和 Penn State 的研究提出 Self-Improvement Memory(SIM),把每次修改的目標、理由和測試成績記下來,換到新模型時再參考紀錄,決定哪些修改要保留或調整。把 Claude Opus 5.5 的程式換到 Gemini 3.8 Flash 的工作任務後,有 SIM 的分數從 68.41 提升到 84.75。
  • 沒有紀錄則是 73.42。10 次程式測試中,SIM 有 9 次得分較高,平均多 2.36 分,顯示記下修改理由有助於把改進帶到新模型。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

Rohan Paul
Rohan Paul@rohanpaul_ai
·5 天前
𝕏

New Google and Penn State paper finds that when one AI rewrites the code that gives another AI its instructions and tools, keeping notes on why each change was made helps the gains carry over to a new model.

LLMs can now rewrite an agent's harness, the code that runs prompts and tools. After a model or benchmark switch, it can score below the original, and its code hides why edits were made.

Self-Improvement Memory, or SIM, logs each edit with the problem it targeted, its reasoning and its measured result. The optimizer reads this log on the new setup to decide which old edits to keep or revise.

When a Claude Opus 5.5 harness moved to Gemini 3.8 Flash workspace tasks, SIM lifted it from 68.41 to 84.75, versus 73.42 without the log. Across 10 repeated coding runs, SIM finished ahead 9 times, by 2.36 points on average.

Store why each harness edit was made and how it scored, and carry that log to new models.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論