论文指出递归自我改进安全评估仍无框架
原标题:This paper argues that no one can call recursive self-improvement safe yet, because we lack even a c...
58AI 研判分
一篇论文指出,递归自我改进(RSI)正被多家 AI 公司推进,但业界既无共识判断其何时安全,也缺乏思考其长期走向的基本框架。作者还以普通用户身份演示,仅用一条高层提示就让 AI 从零训练出一个小型 LLM,说明能力门槛正在快速降低。
报道正文
Rohan Paul (@rohanpaul_ai) · 2026-11-10 23
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
