1
基于 Vaultwarden 和 Keyguard 的自托管密码管理实践
密码管理服务的数据，当然要掌握在自己手里。 查看全文
2
让Token生产更高效：异构混推的关键技术演进与创新实践
商汤大装置异构混推创新实践与技术演进
3
MTFM：美团统一推荐基座大模型在外卖多业务场景的落地实践
美团在 MTGR 基础上提出统一推荐基座大模型 MTFM，首次实现外卖多个主要业务的统一精排模型。
4
智谱 GLM 公开国内大模型首个递归自我改进实践：AI 在十万卡国产集群上自建推理系统
IT之家 9 月 17 日消息，今日，智谱 GLM 团队披露递归自我改进（Recursive Self‑Improvement，简称 RSI）方向首个工程化实践进展，也就是让 AI 自己动手改进自己的运行系统。 具体来说，由 GLM-5.3 驱动的 Infra Agent 完成了 GLM-5.3-F…
5
Agent 安全攻击面分析：风险图谱与防御实践
Agent 安全攻击面分析：风险图谱与防御实践 随着 LLM Agent 从实验室走向生产环境，其安全问题已经从"理论担忧"变成了"现实风险"。2026年，多起 Agent 系统被攻击或滥用的案例表明： Agent 的能力越强，攻击面越大 。本文系统梳理当前 Agent 系统的核心攻击面，提供可操作…
6
美团智播——数字人直播技术创新与实践
美团智播围绕 AI 主播「长得真→动得准→演得活→卖得好」构建了完整技术闭环：真人 1:1 复刻、换装换背景身份不跑偏；动作自然流畅，告别「木偶戏」；边说边动、音画一致；背后还有推理加速技术支撑万路并发开播，让普惠落地成为可能。
7
How to encourage smarter AI use in the classroom
不强制却让多数老师主动用AI？看美国高中怎么把课堂政策变成教学催化剂
This article is from Making AI Work, MIT Technology Review’s limited-run newsletter examining how to apply LLMs across industries. To receive it in yo…
8
9
A pre-flight checklist for shipping a Claude connector
Claude连接器上线前必看的预检清单，教你避开本地测试陷阱，确保生产环境真正可达。
Writing an MCP server is the easy part. Shipping one as a Claude connector means passing four gates that have nothing to do with your business logic: …
10
1ª vez trabalhando com git em um time: tudo que você precisa saber
首次参与团队Git协作？这篇实战指南帮你搞懂PR、Issue和最佳实践，避开新手坑
Faz mais de 5 anos que eu não abria um PR ou issue técnica no Github, mas essa semana tenho aprendido algumas boas práticas e termos que reuni neste a…
11
How to Audit a npm Package for Malware in 10 Minutes
10分钟排查npm包恶意代码，守住环境变量和CI管道不被陌生代码偷走凭据的实用审计流程。
You are about to run npm install some-package and hand a stranger's code full access to your machine, your environment variables, and your CI pipeline…
12
Musical Mirrors: The LLM as Sounding Board in Songwriting
颠覆AI创作常规，让大模型当人声共鸣板，一场人机共创的歌曲实验。
arXiv:2608.13944v1 Announce Type: cross Abstract: This paper examines a use of AI in creative practice as an interpretive sounding board for human-gen…
13
Your agent's "not done" lies as often as its "done"
别轻信AI助手的“已完成”，它可能和“未完成”一样爱说谎，亲手核对产物才是硬道理
There is a well-worn rule for running agents: don't trust the agent when it says it finished. Go look at the artifact. Good rule. We follow it. It did…
14
How to Review AI-Generated Code with Multiple AI Agents
多模型交叉审查AI代码成新趋势，不同模型互查能揪出哪些盲区？一文讲透审查信息要点。
Having one model review code written by a model from a different family is becoming increasingly popular. You might build a feature with Codex, then a…
15
How I Actually Use Claude as a Backend Engineer 🤖
后端工程师亲述 Claude 实战用法：不只生成代码，更要它解释推理过程，值得每一个用 AI 写代码的人学习。
For a while, I treated Claude like a fancy autocomplete — ask a question, paste the answer, move on. That approach worked, but it wasn't until I slowe…
16
7 Backend Security Mistakes Node.js Developers Should Avoidv
Node.js后端必看：7个易踩的安全坑，从密码存储到密钥泄露，逐一拆解避坑要点。
7 Backend Security Mistakes Node.js Developers Should Avoid 🔐 Building a Node.js backend that works is one thing. Building a backend that remains secu…
17
AI to Kids by Letting Them Tweak Local Chatbots [video]
让孩子亲手调教本地聊天机器人，在趣味修改中轻松理解AI原理，寓教于乐。
Article URL: https://www.youtube.com/watch?v=fNkt41q7eqs Comments URL: https://news.ycombinator.com/item?id=49281736 Points: 5 # Comments: 0
18
React Performance Optimization Techniques
React性能优化实战指南，十大技巧直击卡顿痛点，开发者必读的提速手册。
React is known for building fast and interactive user interfaces, but as applications grow, performance issues can appear. Slow rendering, unnecessary…
19
Self-Hosted LLM on a $5 VPS in 2026: What Actually Works
5美元VPS跑自托管LLM，2026年真实可行的硬件与模型选择，量化3B/7B已够用，避坑指南。
"Run your own ChatGPT for five bucks a month" sounds like cheap clickbait. And mostly it is. But the gap between clickbait and reality has narrowed a …
20
Designing tools an LLM won't misuse
别再甩锅给模型了，工具Schema设计才是Agent翻车的重灾区。
Originally published on Loop & Retry — field notes on building LLM agents that survive production. Most agent bugs I've chased weren't in the mode…