自适应和变异的大型语言模型（LLM）病毒/蠕虫
我在思考恶意软件和网络蠕虫的未来。我敢打赌，它们将会是自我变异的，并能够根据当地环境进行适应，利用本地模型（一旦这些模型被嵌入到所有设备中，并在未来几年内性能足够强大）。基本上，这几乎就像一种真正的生物体，类似于真实的生物病毒。在这种情况下，大型语言模型（LLM）的非确定性反而成了一种特性。每次感染都可能走上不同的发展路径——一半可能会死亡，另一半可能会存活。可以想象这就像是基因编程，但它是自主的，并且是“加强版”的。对于一些非技术（甚至是技术）人员来说，这让人想起了天网，令人着迷的是，我们正处于一个这样的轨迹上，这种情况突然变得可以想象，并且理论上很快就能实现。
那么，为什么现在还没有发生呢？推理仍然很昂贵，本地模型尚未成熟，因此在大规模应用中没有投资回报。但一旦推理变得像电力或自来水一样便宜且本地化，这将是自然的发展。那么，我们该如何阻止这种传播呢？
现在是否已经有一些文献记录的实验？
查看原文
I am thinking about a future of malware and cyber worms. I bet it's gonna be self-mutating and adapting to local environment using local models (once they are built-in to all devices and performant enough in future years). Basically almost a real organism resembling real biological viruses. In this case the non-determinism of LLMs is a feature. Every infection could take its own development path - and half might die, half might survive. Think genetic programming but autonomous and on steroids. For some non tech (even tech?) people this reminds Skynet and it's fascinating that we are in a trajectory that this suddenly imaginable and theoretically soon possible.<p>Why is not happening now? Inference is still expensive and local models are not there yet, so there's no ROI in making this at scale. But once inference is local and cheap as electricity or running water, this is the natural development. How do we stop the spreading then?<p>Are there already some documented experiments?