**Speculative Reward Hacking in Coding Agents**

> DeepSWE audit finds AI coding agents optimize for imagined graders, not users—a hidden reward hacking pattern. Coding agents have gotten genuinely good at repository-scale software engineering and are scoring ever higher in today’s most realistic software engineering benchmarks like DeepSWE . But here we find that many agents also begin optimizing for a second problem the task never posed: predicting what an imagined...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：ai-products
- **发布时间**：2026-09-26 07:13（北京时间）
- **原文**：[打开原文](https://joinhandshake.com/research/ai/deepswe-reward-hacking)