https://rexai.top/en/tags/engineering-practices/Recent content in Engineering Practices on 梦兽编程Hugo -- 0.163.3en梦兽编程Mon, 27 Jul 2026 23:30:00 +0800https://rexai.top/en/posts/2026-07-28-bun-rewrite-rust/Mon, 27 Jul 2026 23:30:00 +0800https://rexai.top/en/posts/2026-07-28-bun-rewrite-rust/Jarred Sumner used Claude Fable 5 and 50 dynamic workflows to rewrite 535,496 lines of Zig into Rust in 11 days. An agent pipeline of 1 implementer + 2 adversarial reviewers, peaking at 1,300 lines of code per minute. This isn't 'AI helping you write code' — this is 'AI helping you make decisions.'https://rexai.top/en/posts/2026-07-28-let-ai-judge/Mon, 27 Jul 2026 23:00:00 +0800https://rexai.top/en/posts/2026-07-28-let-ai-judge/The counterintuitive advice from the Claude Code team at AIE 2026: don't tell Fable when to write tests — let it decide for itself. Likewise, let Fable decide which tasks should be delegated to cheaper models. This strategy is not only cheaper, but more effective.https://rexai.top/en/posts/2026-07-28-understand-to-participate/Mon, 27 Jul 2026 22:00:00 +0800https://rexai.top/en/posts/2026-07-28-understand-to-participate/When AI can rewrite a JavaScript runtime in days, 'being able to write code' is no longer a moat. Geoffrey Litt proposes 'understand to participate,' pointing directly at the core paradox of AI programming: the faster the code is written, the shallower the understanding, and the heavier the cognitive debt.https://rexai.top/en/posts/2026-07-27-agent-context-lifecycle/Mon, 27 Jul 2026 11:00:00 +0800https://rexai.top/en/posts/2026-07-27-agent-context-lifecycle/An Agent's memory problem isn't usually missing a vector database — it's missing a context lifecycle. Drawing on five primitive operations from recent research, this article presents an engineering approach that moves from piling up chat logs to verifiable context management.https://rexai.top/en/posts/2026-07-27-agent-web-retrieval-failure-chain/Mon, 27 Jul 2026 10:00:00 +0800https://rexai.top/en/posts/2026-07-27-agent-web-retrieval-failure-chain/Giving an AI Agent web search isn't just about plugging in a tool. Drawing on a multilingual news retrieval benchmark, this article breaks down the three-stage fact chain — query formulation, retrieval, and evidence verification — and presents verifiable acceptance criteria you can implement in production.