1
Lucid Train
还在为接手老代码发愁？Lucid Train帮你快速构建系统设计，理清代码库架构，开发效率直接翻倍！
Build system design for new and existing codebase Discussion | Link
2
Show HN: Visual way to understand things in parallel
用画布把 AI 对话变成可分支的知识树，随时展开术语和疑问，所有相关线程一目了然，不用切换标签页。
Hey HN! Really excited to be showing what I think is a better way to understand complex topics with AI. You start a chat with your question, and whene…
3
Show HN: 3D Engine for Rust Programs
Rust生态新3D引擎，集GUI与可视化于一体，适合仿真与科学计算场景。
I mostly stabilized the API for this 2 years ago. Since then, I've made occasional performance improvements, and feature additions. It's built to supp…
4
Run Rob Run: Building a Music-Reactive Goo with Three.js and WebGPU
用Three.js和WebGPU打造会随音乐律动的液态“Goo”，从软体到立方体的滚动变形，技术拆解太带感了
Exploring the techniques behind an audio-reactive 3D scene, from custom geometry deformation and music analysis to scroll-driven morphing, damping, an…
5
Show HN: Verified business dashboards inside ChatGPT and Claude via MCP Apps
MCP官方扩展让ChatGPT和Claude直接渲染交互式仪表盘，数据可视化一步到位。
Article URL: https://www.corpusiq.io/docs/hermes/mcp/mcp-apps-interactive-ui Comments URL: https://news.ycombinator.com/item?id=49380035 Points: 2 # C…
6
ARGOS v0.0.1 is live: a digital twin of Kefalonia
用开源数据构建的凯法利尼亚数字孪生地图，零成本托管，交互探索地理信息。
Three weeks ago I started building a map that argues back. Today it is public. 🗺️ argos-geo.org/map What you can do: Click any building, road, beach, …
7
If-Else or Boundaries?
用可视化节点编排消息自动化，以边界替代复杂if-else，支持AI代理与人工控制，落地OWASP防过度代理
Series: From Visual Flows to AI-Orchestrated Automation · Part 03 A chatbot rarely becomes difficult because of its first if statement. The problem st…
8
谷歌在搜索和 Gemini 中推出多款全新 AI 学习工具，含交互式可视化内容、3D 模拟等
谷歌新推AI学习工具，上手搜pH值就能玩转3D交互模拟，边玩边学太香了。
IT之家 8 月 20 日消息，谷歌当地时间周三宣布，将在搜索和 Gemini 中推出一系列全新的学习工具，包括 AI 生成的交互式可视化内容、3D 模拟、专门的学生中心、自定义练习测验等。 IT之家注意到，此次推出新的学习功能，是谷歌进一步推动 Gemini 成为学生学习和备考首选 AI 助手的又…
9
GPT 5.6 Sol is the best "vision" model OpenAI ever released
OpenAI新视觉旗舰GPT-5.6 Sol登场，UI智能体与3D感知实力拉满，视觉AI爱好者不容错过。
Article URL: https://blog.roboflow.com/openai-gpt-5-6/ Comments URL: https://news.ycombinator.com/item?id=49329575 Points: 204 # Comments: 105
10
LLM City – 3D render of all Kimi K3's weights as 2.5mm tiles
把Kimi K3的权重渲染成3D城市：24.9万个张量、896个专家一目了然，AI内部结构从未如此直观。
Article URL: https://magik.net/llmcity/ Comments URL: https://news.ycombinator.com/item?id=49333151 Points: 2 # Comments: 1
11
Show HN: GitFC – Turn your GitHub profile into a football card
输入 GitHub 用户名，就能把代码贡献生成 EA FC 风格球星卡，看你的开发者属性像哪位球员。
I Built GitFC because I always wanted to see how an activity of Github would look like if treated like football player stats. Here you include your gi…
12
Show HN: Rungraph – See your AI coding-agent runs as a graph
把AI编程代理的每次运行变成可视化图谱，快速定位问题，提升调试效率。
Article URL: https://github.com/fayzan123/rungraph Comments URL: https://news.ycombinator.com/item?id=49321388 Points: 1 # Comments: 0
13
Show HN: I built a spatial node canvas to fix LLM context drift
用空间画布可视化对话节点，直观解决大模型上下文漂移痛点
Article URL: https://treequence.ai Comments URL: https://news.ycombinator.com/item?id=49310343 Points: 4 # Comments: 0
14
AI-Lab: Classical AI and search algorithms implemented in Python
经典AI与搜索算法的Python实现库，带透明可视化、自动化基准测试和18个交互演示，适合学习与研究。
Article URL: https://github.com/ob22a/ai-lab Comments URL: https://news.ycombinator.com/item?id=49304392 Points: 1 # Comments: 0
15
截至今年 8 月，科技行业裁员 12.6 万人已超去年全年
实时追踪全球科技裁员动态，数据清晰直观，助你快速把握行业走势、理性规划职业。
IT之家 8 月 15 日消息，据外媒 Futurism 当地时间 14 日报道，2025 年，全球 278 家科技公司共削减了 122606 个面向高技能专业人士的岗位。 这其中，亚马逊和 Meta 等资金雄厚的大型企业是裁员潮的重要推动者，这些公司一边大举投资 AI，一边大规模裁员。 去年科技行…
16
Show HN: My Claude subscription did $5,868 of API-equivalent work last month
把Claude订阅用量换算成API等效花费，30天账单一目了然，帮你看清订阅值不值
Article URL: https://github.com/dpro10/cookbook-meter Comments URL: https://news.ycombinator.com/item?id=49288618 Points: 1 # Comments: 0
17
Show HN: Visual knowledge graphs using Ollama and Embeddings
用Ollama和Embeddings本地构建可视化知识图谱，开源玩法值得一试。
Article URL: https://github.com/punnerud/Local_Knowledge_Graph Comments URL: https://news.ycombinator.com/item?id=49270102 Points: 1 # Comments: 0
18
NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
用可视化拆穿大模型越狱的底层套路，看透AI安全盲区，值得研究者一读。
arXiv:2509.03985v2 Announce Type: replace-cross Abstract: In deployment and application, large language models (LLMs) typically undergo safety alignme…
19
Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentation
一眼看懂Transformer内部机制，用交互可视化亲手演示LLM的推理过程
arXiv:2408.04619v2 Announce Type: replace-cross Abstract: The Transformer architecture underpins modern large language models powering state-of-the-ar…
20
Show HN: Airship – Figma-Like Visual Editor for Claude Code, Codex and OpenCode
给AI编程助手配上Figma式可视化编辑界面，Airship直接对接本地端口，让Claude Code、Codex与OpenCode的操作流程更直观高效。
I wanted to experiment with my UI like I do in Figma, without having to rebuild it in a separate design tool. So I built Airship. It lets you prototyp…