📰 2026-05-03 06:30 更新
🔸 The agent harness belongs outside the sandbox / 座席线束属于沙盒之外
🔗 The agent harness belongs outside the sandbox
🔥 19 points
原文:
An agent harness is the loop that drives an LLM. It sends a prompt, gets a response, executes the tool calls the model requested, feeds the results back, and repeats until the model says it’s done. Every production agent has one. The question is where it runs. There are two answers. They have different security properties, different failure modes, and different implications for what the agent can do. The tradeoffs also look different depending on whether you’re building a single-user agent (o…
译文:
座席线束是驱动LLM的循环。它发送提示，获取响应，执行工具调用请求的模型，反馈结果，并重复，直到模型表示完成。每个生产代理都有一个。问题在于它在哪里运行。答案有两个。它们具有不同的安全属性、不同的故障模式以及对代理可以执行的操作的不同含义。权衡取舍看起来也不同，这取决于 您是否正在构建单用户代理（或…
自动更新 · 正文抓取 · 双语翻译