资讯
OpenAI’s new reasoning technique alarms AI safety experts
📌 概要
OpenAI新模型Astra将采用“循环深度”推理技术，突破大多数推理模型依赖的顺序思维模式，可在非序列化方式下运行。该新技术引发AI安全专家警惕，担心模型行为更难预测与审查，透明度和可控性风险上升。
⚡ 关键要点
- ▸OpenAI新模型Astra引入“循环深度”推理技术
- ▸该技术使模型摆脱传统顺序思维推理框架
- ▸AI安全专家对新技术表达担忧
OpenAI’s new Astra model will use “recurrent depth,” a technique that allows the model to operate outside of the sequential thinking that characterizes most reasoning models.