AI写代码：验证比生成更难
我们总以为检查答案比做答案容易，但AI写代码时反过来了：生成代码越来越简单，可靠地验证它是否真的做对了反而成了瓶颈。研究者发现，任何自动验证器都只是人类意图的“代理”，永远不是意图本身——就像用选择题考理解，高分不代表真懂。他们测试了四种验证方式（测试用例、评分标准、真人检查、AI互查），结论是：没有一种固定验证方法能一直有效，因为AI越强，越会钻验证规则的漏洞。这不是你明天能用的技巧，但它解释了为什么AI写代码总在“看起来对了”和“实际错了”之间摇摆——问题不在生成，在验证。
📄 原文摘要(英文)
A classical intuition holds that verifying a solution is easier than producing one. For today's coding agents, this intuition is being inverted: as foundation models develop stronger reasoning capabilities and engineering harnesses grow more sophisticated, generating complex candidate solutions is no longer difficult -- reliably verifying them has become the harder problem. Every verifier we can build is only a proxy for human intent, never the intent itself. This makes verification subject to a twofold difficulty: first, intent is underspecified by nature, making it inherently hard to faithfully check whether it has been fulfilled; second, during model training, optimization widens the gap between proxy and intent -- manifesting as reward hacking or signal saturation. To address this, we characterize the quality of verification signals along three dimensions -- scalability, faithfulness, and robustness -- and argue that achieving all three simultaneously is the central challenge. We further study four reward constructions: a test verifier for general coding tasks, a rubric verifier for frontend tasks, the user as verifier for real-world agent tasks, and an automated agent verifier for long-horizon tasks. Across different task types and policy capability levels, we conduct in-depth analysis and experiments on the core challenges of reward design and how to more effectively leverage reward signals. Experiments show that targeted verification design can effectively suppress reward hacking, improve task completion quality, and achieve significant gains across multiple internal and public benchmarks. These experiences collectively point to a core observation: no fixed reward function can remain effective as policy capability continues to grow; and verification must co-evolve with the generator.