跳到正文
𝕏 elvis(x.com)·· 4 天前精選品質評分69
重點導讀

如果 AI 助理沒有被教怎麼學習,還能不能自己找出改進方法?

  • MIT CSAIL 和 University of Tübingen 的研究讓固定不變的模型使用簡單工具,自己設計練習遊戲、觀看另一個模型遊玩,再修改對方的提示詞和技能檔案。
  • 模型看不到真實任務或驗證分數,也沒有收到學習指示,但有能力的模型仍能設計不同難度的遊戲、比較做法,並在規則藏起來的遊戲中進步。
  • 研究也提醒,沒有明確安排自我改進流程,不代表具備工具的模型就不會自行改進。

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:

推薦理由

研究顯示,具備簡單工具的模型可能自行摸索改進方法,為評估模型能力與安全風險提供具體案例。

elvis
elvis@omarsar0
·4 天前
𝕏

Do LLM agents still need to be told how to self-improve?

A new paper from MIT CSAIL and the University of Tübingen tests this directly.

They give a frozen model a compute budget and simple tools. It can write practice games, watch another copy of itself play them, and edit that copy's prompt and skill files. It does not see real tasks or validation scores, and it is not told how to learn.

Capable models built a working learning procedure on their own and improved on held-out games with hidden mechanics.

Models from different families arrived at similar strategies. They wrote games at a calibrated difficulty, ran controlled A/B comparisons, built their own validation suites, and spent more effort on harder tasks. The text files they produced also improved play on external benchmarks with different horizons, mechanics, and 3D navigation.

This matters for safety as well. Leaving out an explicit self-improvement loop does not stop a capable model from improving itself when it has the tools.

https://t.co/EJXwIYrGjd

Chat with Paper: https://t.co/La9hjcKD7k

推文來源 · X (Twitter)在 X 參與討論
來源: elvis (x.com)
在 X 查看推文

讀者討論

理性交流 · 即時討論