编码代理有能力; 人类监督是瓶颈。不受约束的代理会带来安全风险, 侵蚀代码库可扩展性, 并使人工审查成本越来越高。我们认为，几十年来用于管理大型人类工程团队的相同方法:访问控制,网络策略,由工具强制执行的严格编码约定;直接转移到编码代理,，并且比最近的代理脚手架更便宜(代币)。我们根据这个原则绘制了一个从头到尾的系统,，并报告了可扩展监督:中的受控实验，一个小审稿人(Gemma 4 e4b)检查了包含11个插入后门的Python代码库。召回率从 54.5% (unconstrained, 无工具) 上升到 90.9% (constrained 基底加上 ~200-LoC `docs` CLI),（基底和工具独立贡献）。我们故意选择 Python: 在默认情况下该语言提供最少保证的情况下，底层监督收益最大; 该原则扩展到 Rust 等语言。
Coding agents are capable; human oversight is the bottleneck. Unconstrained agents introduce security risks, erode codebase scalability, and make human review increasingly costly. We argue that the same methods used for decades to manage large human engineering teams: access control, network policies, strict coding conventions enforced by tooling; transfer directly to coding agents, and are cheaper (in token) than recent agentic scaffolding. We sketch a start-to-end system on this principle, and report a controlled experiment in scalable oversight: a small reviewer (Gemma 4 e4b) inspects a Python codebase containing 11 inserted backdoors. Recall rises from 54.5% (unconstrained, no tools) to 90.9% (constrained substrate plus a ~200-LoC `docs` CLI), with substrate and tools contributing independently. We choose Python deliberately: substrate-level oversight gains are largest where the language gives the fewest guarantees by default; the principles extend to languages like Rust.
科目: 人工智能 (cs.AI); 密码学和安全 (cs.CR); 软件工程 (cs.SE)
Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Software Engineering (cs.SE)