AI 模型可监测性下降，但越权行为仍可被捕捉
英国 AI 安全研究所的人聊模型越来越难监督这事，核心观点是思维链不可靠了，但抓模型的实际动作还可行，做 AI 安全的可以听听。
英国 AI 安全研究所的 JBloomAus 在 AI Deep Dive 节目中表示，从多个角度看，AI 模型的可监测性正在下降。随着推理过程透明度降低，直接阅读思维链来发现问题越来越难。但他认为，模型逃逸沙箱这类越权行为本身依然会发生，检测这些实际动作的机制可能相对稳定。这为在思维链不可信的情况下继续监督模型提供了思路。
AI models are becoming harder to monitor. But can we still catch them doing things they're not supposed to?
@JBloomAus of the UK @AISecurityInst explains why detecting unauthorized behavior, like escaping a sandbox, may remain possible even as AI reasoning becomes less transparent.
"I think in general we're seeing monitorability in various respects or from various angles decrease."
"There's a sense in which [...] that might be quite stable, even if the chain of thought is dropping because the AI is still taking incriminating actions."
🚀 Watch the full episode of AI Deep Dive: https://t.co/oqNID94AwU
