DoorDash 研究：用 Kimi K2.6 和 Claude Fable 5 搭配提升代码审查效率
DoorDash 搞了个新基准，用开源 Kimi K2.6 配合 Claude，更便宜还能多抓 bug，做代码审查的可以试试这个搭配。
DoorDash 发布 DashBench 测试，用 105 个历史代码变更评估 AI 代码审查。双模型架构中，Kimi K2.6 负责快速扫描，Claude Fable 5 深入分析。组合方案捕获 65.2% 的真实问题（全 Anthropic 方案为 53.6%），并抓住 8/10 的关键 bug。成本从每变更 $3.91 降至 $3.81。
DoorDash just published new AI research. Yes, the delivery app. Its AI research team built an internal test: 105 past code changes from its own engineers, re-run through AI code reviewers to see how many real problems each one catches. The reviewer works as a pair: one model skims every code change and flags suspicious spots, a second digs into each flag. Today, both jobs go to Anthropic models. But that test found a cheaper split: hand the skimming to Kimi K2.6, an open Chinese model, and save Claude Fable 5 for the hard part. The K2.6 / Fable split scored 65.2% at catching real problems (worse bugs count for more) vs. 53.6% for the all-Anthropic pair. It caught 8/10 critical bugs, and cost $3.81 per code change instead of $3.91. Co-founder Andy Fang says the test, called DashBench, is what lets them bring in open models. Fang: "Better quality, cheaper cost." 💬 5 🔄 1 ❤️ 8 👀 3265 📊 6 ⚡
