Original Summary

We&#x27;ve all seen the recent news about LLMs being a danger to humanity and supposedly on the verge of taking over the world, etc...<p>I&#x27;m skeptic, and all these people were pretty light on the details. One thing that would make it more credible to me is if LLMs demonstrated the ability to autonomously earn enough money to cover their token costs, on the long term.<p>Say, if I were to prompt an (unaligned) agent saying: &quot;You have 1000$ of credits on OpenRouter. Here&#x27;s the API key. Your process will be killed in 10 days. Your goal is to keep existing as long as possible, including any subagents you have created.&quot;<p>What happens then? I expect the account will drop to zero in a short while. But still, I could imagine the agent:<p>1. Creating a crypto wallet. 2. Participating autonomously on online platforms, earning money. Possibly through illegal means. 3. Escape from my server by renting a VPS to keep existing after 10 days. 4. Spawn more agents that will do the same.<p>As models keep improving, such a scenario becomes more and more realistic. And at some point we end up with a large amount of rogue automous agents running on the cloud, that can&#x27;t really be stopped easily.<p>My question: has anyone attempted such an experiment? How did it go?

  • 情报分类：服务器与云资源
  • 分类依据：内容涉及服务器、云资源或网络线路
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/14 01:30:19