Cursor 团队介绍其智能体 harness 调优细节
we've been hard at work tuning our harness for each model, making sure the model doesn't go in loops, putting large tool results in files to let the agent grep
Cursor 团队成员 Balta 表示团队一直在为每个模型调优 harness，具体做法包括避免模型陷入循环、把较大的工具返回结果写入文件让智能体用 grep 检索以免撑爆上下文，以及在循环中加入提醒引导智能体行为。他同时表示很高兴看到用户喜欢改进后的智能体 harness，后续还有更多更新。被引用的推文称 Matt Maher 测试了前沿模型在 Cursor 与其他 harness 中的表现，Cursor 平均提升模型性能 11%，其中 Gemini 从 52% 升至 57%、GPT-5.4 从 82% 升至 88%、Opus 从 77% 升至 93%。
推荐理由
AI 评分 58
原文披露了 Cursor 智能体 harness 的三项具体调优手段，可据此理解同一模型在不同 harness 下表现差异的来源。
主题
查看原帖Matt Maher tested frontier models in Cursor v. other harnesses. Cursor boosted model performance by 11% on average: Gemini: 52% → 57% GPT-5.4: 82% → 88% Opus: 77% → 93% His benchmark measures how well models implement a 100-feature PRD. @cursor_ai consistently outperformed. https://t.co/hrjCmWMNKN
正文
当前显示原文，中文全文译文尚未就绪。
we've been hard at work tuning our harness for each model, making sure the model doesn't go in loops, putting large tool results in files to let the agent grep through it and not overload its context, and adding reminders in the loop to steer the agent towards favorable behavior.
im stoked to see people enjoying our improved agent harness, we have more coming!