# AI 能力越强，越需明确其该做与不该做的边界

- 来源：OpenAI (@OpenAI)
- 发布时间：2026-03-26 01:20
- AIHOT 链接：https://aihot.virxact.com/items/cmnw1yuaa015rslc39jsbe7wj
- 原文链接：https://x.com/OpenAI/status/2036855694906057079

## AI 摘要

OpenAI 研究员 w01fe 与主持人 Andrew Mayne 探讨 Model Spec，解析这一定义模型预期行为的公开框架如何在实践中运作：包括解决冲突指令的指挥链机制，以及该规范如何随实际使用、反馈和新能力持续演化。

## 正文

The more AI can do， the more we need to ask what it should and shouldn't do.

OpenAI researcher @w01fe joins host @AndrewMayne to explore the Model Spec， the public framework that defines how models are intended to behave.

They break down how it works in practice， from the chain of command that resolves conflicting instructions to the way it evolves over time through real-world use， feedback， and new model capabilities.