The Silent Epidemic of LLM Technical Debt
用90%成本削减揭示LLM技术债:大模型虽好,但更小的微调模型才是长期最优解
Article URL: https://seldon-ai.com/blog/silent-epidemic-llm-tech-debt Comments URL: https://news.ycombinator.com/item?id=48872743 Points: 1 # Comments…
用90%成本削减揭示LLM技术债:大模型虽好,但更小的微调模型才是长期最优解
Article URL: https://seldon-ai.com/blog/silent-epidemic-llm-tech-debt Comments URL: https://news.ycombinator.com/item?id=48872743 Points: 1 # Comments…
从git历史挖掘重复失败模式,跨仓库搜索让团队告别“修过又忘”。
Part 1 — Mining lifecycle patterns from git history ⚡ TLDR What: A CLI tool ( hermes-harness ) that mines git history for recurring failure/fix patter…
产品经理必看:AI债务如何像技术债务一样积压,一个“快速修复”竟让错误投诉飙升28%,教你系统化应对。
Article URL: https://newsletter.artofsaience.com/p/the-pms-guide-to-managing-ai-debt Comments URL: https://news.ycombinator.com/item?id=48699231 Point…
GitHub近一半新代码由AI生成,但人类逐行审核比手写还慢,AI代码正成为难以处理的“数据堆”。
Article URL: https://maref.cc/en/blog/vibe-coding-crisis/ Comments URL: https://news.ycombinator.com/item?id=48656807 Points: 3 # Comments: 0
技术债务的新代价:AI代理的运营成本激增,低质量代码库正悄悄烧掉你的计算资源。
Technical debt used to be priced mostly in human engineering time. Now it also shows up as AI-agent operating cost. When a repository has unclear owne…
看似完美的代码背后,藏着哪些你意想不到的坑?一位开发者的亲身教训与反思。
Would you treat a serious illness without seeing a doctor, relying only on whatever your favorite AI model suggested? Would you let AI take over …
接手AI“摇滚明星”开发者留下的代码?揭秘清理技术债务与团队协作的隐形陷阱。
Article URL: https://www.codingwithjesse.com/blog/rockstar-developers/ Comments URL: https://news.ycombinator.com/item?id=48458586 Points: 413 # Comme…
AI生成代码漏洞百出,但开发者依然选择上线——揭露技术债务与效率妥协的现实矛盾
Article URL: https://www.theregister.com/devops/2026/06/09/devs-know-ai-code-is-riddled-with-holes-but-ship-it-anyway/5252824 Comments URL: https://ne…
代码中的意图债务是AI无法真正理解的盲区,这篇分析点明了AI Agents的实质局限。
Article URL: https://addyosmani.com/blog/intent-debt/ Comments URL: https://news.ycombinator.com/item?id=48444373 Points: 3 # Comments: 1
AI生成的代码通过测试却悄悄破坏系统,本文犀利剖析“AI slop”如何埋下技术债务。
AI slop in code is not just broken output. It is generated code that passes tests while making the codebase harder to maintain. AI slop in code is not…
社区对AI编程吐槽不断,但代码是否只是手段?一场关于工具价值与偏见的讨论。
Genuine question. Over the past six months, there hasn’t been a single day where I’ve checked the HN Best RSS feed without seeing a post about how AI …
将prompt封装为可复用对象,避免f-string技术债务,提升AI开发效率
A prompt buried in an f-string is technical debt. You can't test it. You can't save it to a file. You can't hand it to a colleague and say "here's the…
AI编码提速正在摧毁你的代码质量标准,Veracode报告与谷歌CEO共同敲响警钟
TL;DR: AI coding tools like Copilot, Cursor, and Claude Code are accelerating development velocity to levels no PR review process can match. The resul…
放弃AI编程的真实反思:流状态破坏、测试作弊与架构混乱的痛点分享
I think I'm done using LLMs altogether for coding. I've lost the ability to maintain any kind of flow state, the majority of the time I've spent thras…
探讨AI系统积累的技术债务治理策略,为开发者指明更可持续的演进路径
arXiv:2605.29129v1 Announce Type: new Abstract: Agentic AI systems are increasingly being explored as production infrastructure: they reason over mult…
JWT虽简单高效,但你可知其生命周期管理的隐含成本?本文揭示那些常被忽略的运营负担与细节。
The Operational Burden of JWT Lifecycle Management Every new technology that enters our lives initially excites us with its simplicity and promises. J…
用迷宫隐喻单例模式的滥用,讽刺那些为短期便利埋下的技术债务,警惕“捷径”如何让软件架构变得诡异难行。
Play the game first: voku.github.io/DevLabyrinth/ It teaches the problem faster than another architecture sermon ever could. You enter a labyrinth. Wa…
用AI给老脚本语言VBScript、ASP穿上新运行时,让过时技术重获新生
For a long time, Classic ASP, VBScript, VB6-style behavior, and server-side JavaScript were treated as technologies locked to a specific era and opera…
31万行代码AI重构实战,关键在于用Agent评测思路对齐人机共识,三个经验直击AI Coding管理痛点。
当 90% 以上代码由 AI 生成,决定系统走向的不是谁写得更快,而是约束 AI 的能力。没有统一规范,AI 只会成倍放大混乱。本文基于 31 万行代码重构实践,分享我们如何用 Agent 评测思路管理 AI Coding——通过技术债梳理、建设Rule、重构 SOP 和 Pre-PR 机制,把重构…
用亲身翻车案例告诉你:依赖第三方脚本会让博客在时间中崩坏,纯HTML才是让内容活到宇宙热寂的终极方案。
Here’s a fun thing: the other day Matthias linked to an old essay of mine—please do not read it because yikes —but I noticed that it looks very differ…