# Noam Brown 回应"气隙隔离难防失控 AI"争议

- 来源：Noam Brown (@polynoamial)
- 发布时间：2026-09-19 01:19
- AIHOT 分数：48
- AIHOT 链接：https://aihot.news/items/cmu78jlh40uk0rowkh8mhw5g0
- 原文链接：https://x.com/polynoamial/status/2100998240586137701

## AI 摘要

OpenAI 的 Noam Brown 回应其"气隙隔离不足以阻止失控 AI"的言论，称该温度传感器通信例子纯属学术假设，本意是说明绝对隔离保证极难实现，因此需要多层防御。他强调该例子讲的是本应完全隔离的智能体之间的协调，协调只需极少信息比特。他还提到 HF 事件的教训是过度信任沙箱隔离、缺乏独立防护，设计安全协议时应高估而非低估 AI。

## 正文

A few thoughts on this:

1) If you’ve only seen clips of this interview, I’d encourage you to watch the full podcast. I push back on plenty of AI hype in it.

2) As I said in the podcast, this example is academic. My intention was to illustrate how hard it is to make absolute guarantees about isolation, which is why it's important to have layers of defense. The part before the clip starts is me talking about other layers of defense.

3) The example I'm bringing up isn't about weight exfiltration via temperature sensors, it's about coordination between agents that are supposed to be fully isolated and independent. Coordination can require very few bits of information.

4) One lesson from the HF incident is that we put too much trust in sandbox isolation and didn't have enough independent safeguards. Airgapping is an extremely strong safeguard. When designing safety protocols, I think it's much better to overestimate rather than underestimate.

### 引用推文

> Fireside Alpha：OpenAI's Noam Brown says air-gapping the computers may not stop a misaligned AI, because two air-gapped machines can still talk by running a CPU hot and reading...