1
NeST: Neuron Selective Tuning for LLM Safety
大模型安全新方案：通过神经元选择性调优NeST精准提升LLM安全性，不牺牲性能。
arXiv:2602.16835v2 Announce Type: replace-cross Abstract: Safety alignment is essential for the responsible deployment of Large Language Models (LLMs)…
2
把 Sa-Token 搬到 NestJS 生态：xlt-token 1.0 的几个设计取舍
从Java鉴权到NestJS，xlt-token精细化处理401状态，让前端精准区分六种未登录原因。
最近发布了 xlt-token@1.0.0-rc.1 ，一个为 NestJS 设计的 Token 鉴权库，灵感来自 Java 生态的 Sa-Token 。 仓库： github.com/xiaoLangtou/xlt-token 功能列表看起来不复杂——登录、登出、踢人、权限校验、会话存储——但动手…
3
"NestJS authentication in 5 minutes"
5分钟实现NestJS JWT认证，简洁高效，开发必备实战指南
NestJS Authentication in 5 Minutes 🔐 Authentication in NestJS sounds complicated at first… But the actual flow is surprisingly simple 👇 User Login ↓ V…
4
Same NestJS Prompt via Two AI Toolchains. One Returned 6 Security Errors. Here's What Both Missed.
同一NestJS提示词，Claude和Gemini生成的代码安全错误数不同：一个多出6个，但两者都漏掉了关键漏洞。
Same prompt. Anthropic's API returned 6 security errors. Google's tooling returned 2. I gave Claude Sonnet 4.6 and Gemini 2.5 Flash the identical prom…
5
Injeção e Inversão de Dependência e como o NestJS gerencia tudo isso
用依赖注入告别硬编码依赖，NestJS如何通过容器实现优雅管理
No NestJS, praticamente toda a arquitetura do framework gira em torno de um conceito central: a inversão de controle através da injeção de dependência…
6
MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training
Muon优化器新升级MONA，融合Nesterov加速突破局部极小，提升大模型训练效率
arXiv:2605.26842v1 Announce Type: new Abstract: The Muon optimizer has recently offered a promising alternative to AdamW for large language model trai…
7
Google's Second-Gen Wired Doorbell Is Under $100 Right Now
谷歌第二代有线门铃Woot现价仅97.99美元，比原价省82美元，历史最低价，适合Google Home用户升级智能家居。
A much easier upgrade to justify for Google Home users.