Cerebras：再强的模型也救不了糟糕的 harness
原标题：A Smarter Model Won’t Save Your Bad Harness
AI 摘要
Cerebras 博客发文指出，智能体由模型、harness（运行框架）和环境组成，harness 决定模型能看到什么、能执行哪些动作以及结果如何反馈。文章引用论文数据称，同一 Claude Opus 4.5 模型在标准化 SEAL 框架下 SWE-bench Pro 得分为 45.9%，经 Claude Code 运行则达 55.4%，说明基准结果属于模型与 harness 的组合。文章还指出 harness 的规划、重试、验证等环节都会增加模型调用，因此快速推理对 harness 性能至关重要。
正文节选
An agent is roughly a model inside a harness, operating in an environment. The model supplies the intelligence. It reasons, makes decisions, writes code, and decides what actions to take next. The environment is the actual computer, repository, browser, or container where this work happens, and the user (sometimes another agent) is the one providing the goals and providing guidance when needed. The harness decides what the model can see, what actions it can take, how results get fed back into th