wangjstu

出海Junior engineer，出海探索学习ing。 终身学习者。

[wangjstu @wangjstu]

@jayfang1993 是真的，所以阿里、蚂蚁都在加班

[Machine Learning Mastery @TeachTheMachine]

Pretraining a Llama Model on Your Local GPU

https://t.co/o77mLpaPir

[Andrew Ng @AndrewYNg]

New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter decisions about deployment. This course is built in partnership with @AMD and taught by @realSharonZhou.

You'll see how transformers generate text one token at a time, how the model decides which earlier words matter most when predicting the next one, and how techniques like quantization speed up inference on GPUs. This is not a video-only course; interactive visualizations throughout let you play with these concepts and build intuition that sticks.

Skills you'll gain:
- Understand why LLMs hallucinate, and RAG and chain-of-thought shape what they generate
- Look inside the model to see how attention and layers combine to predict the next token
- Diagnose inference bottlenecks and learn the techniques that speed up transformers on GPUs

Join and understand what's really happening inside your LLMs: https://t.co/oS6ekeHsIw

[ginobefun @hongming731]

https://t.co/s3TSzVqDI6

[wangjstu @wangjstu]

https://t.co/ws3QybTEty

[CrAIg Walls @habuma]

Over the past few weeks, I’ve been publishing a growing series of Spring AI Recipes covering agents, MCP, A2A, memory, workflows, tools, and more.

There’s now a central place to find all of the recipes in one spot: https://t.co/VYdJ96wtwe

#SpringAI #Java #AgenticAI #MCP #LLM

[Baeldung @baeldung]

Java Concurrency Series: https://t.co/cxmHbxDXvO

[wangjstu @wangjstu]

哇，别人已经做了我想做的，我想做的，commit 了10来次，就停了….

[Joruno @wsl8297]

写技术文档、梳理业务逻辑时，总少不了流程图、架构图这些“直观表达”。问题是：画图太耗时。

Smart Excalidraw 是一款开源工具，让你用自然语言直接生成专业级、结构清晰的图表，把“画图”变成“描述”。

它内置智能箭头与布局优化，自动避免连线交叉、排版错乱；支持流程图、架构图、时序图、思维导图等 20+ 种图表类型，一次生成就很像样。

GitHub：https://t.co/Kp73IQp7UK

同时集成 Excalidraw，生成后可继续自由微调样式与细节；数据仅保存在本地浏览器，隐私更安心。

项目还提供在线演示：配置一个 AI API 密钥即可上手。推荐使用 Claude Sonnet 4.5，也支持本地部署运行。

[wangjstu @wangjstu]

https://t.co/DlAHXs6hUg

[Thariq @trq212]

I put a lot of heart into my technical writing, I hope it's useful to you all.

📌 Here's a pinned thread of everything I've written.

(much of this will be posted on the Claude blog soon as well)

[Piotr Mińkowski @piotr_minkowski]

I created my Claude Code template repo for the Spring Boot app with instructions, skills, and subagents.💡
It is desired to create an app that connects to the DB, is deployed on Kubernetes, and runs tests with Testcontainers, and some others 👉https://t.co/7dLMj8KHGB

[Cos(余弦)😶‍🌫️ @evilcos]

🦞OpenClaw 极简安全实践指南 v2.8 Beta 出来了，数个独立 OpenClaw 来回测试了几百个小时，覆盖 Gemini/Opus/Kimi/MiniMax/GPT 等最新模型。

https://t.co/qF7SmZaL6Y

v2.8 Beta 先完全独立，包括对应给人类参考的巡检脚本。如果你感兴趣，可以尝鲜👀

⚠️注意，用之前务必仔细阅读仓库的 README。

[avrl ☘ @avrldotdev]

https://t.co/Lk2vjlJANB

[Tom Dörr @tom_doerr]

Tutorials for building applications from scratch

https://t.co/zyqXPntGdV

[wangjstu @wangjstu]

A copilot sells the tool. An autopilot sells the work.

[ℏεsam @Hesamation]

you really NEED to read this if you don’t want your product to be headshot by a tiny Claude feature.

[ℏεsam @Hesamation]

this is a useful repo if you’re starting with Claude Code or Codex. it has a list of:
— essential documentations
— best practices and workflows
— videos you might learn from

https://t.co/lzj9fTRa9S

[@abdimoalim.bsky.social @abdimoalim_]

JVM internals (by James D. Bloom): https://t.co/VjmCkTYhuI

[Docker @Docker]

Running OpenClaw locally? Do it safely.

This walkthrough shows how to run it inside Docker Sandboxes with Docker Model Runner:
- Isolated microVM
- No exposed API keys
- Controlled network access
- Fully private, local AI setup

Secure agent workflows in ~2 commands.

Read → https://t.co/RZh2qp7eSi

[Siva @sivalabs]

Looking for Spring Boot Crash Course with examples?

Look no further! 👇
https://t.co/JEJAXhYtqH

[Baeldung @baeldung]

The Java Weekly is out: https://t.co/VxZZ4SF4mI