遞迴自我改進(RSI)的安全性仍無法定論,因為目前缺乏清楚的方法判斷它會帶來什麼結果。
- 風險與安全條件:AI 公司已開始追求 RSI,但對何時才算安全尚無共識;安全工作坊的專家也提出了不同條件。
- 賽局分析:作者以雙人賽局指出,RSI 競賽只在部分風險程度下構成囚徒困境;風險高時,雙方都暫緩行動可以是穩定結果。
AI 伴隨問答
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:
This paper argues that no one can call recursive self-improvement safe yet, because we lack even a clear way to think about where it leads.
Recursive self-improvement, or RSI, means an AI builds a better AI, which builds a better one, and so on. AI companies are starting to pursue it, with no shared view of when it would be safe.
As an ordinary user, the author got an AI to train a small LLM from scratch from 1 high-level prompt. At a https://t.co/I8EjyOkuK6 safety workshop, experts listed very different conditions for RSI because they imagined very different outcomes.
His 2-player game shows the RSI race is a Prisoner's Dilemma only at some risk levels. At high risk, both sides holding back is a stable outcome, so waiting together can work.