Hi friends! Awesome news! We had started our playtest. It will last for about a month, maybe more, depending on demand. The goal of this playtest is to check the game from Chapter 1 to Chapter 3, and collect your feedback. Please write all your thoughts in the game's community hub. You can playtest Shop Crush on the game's Steam page. Comments URL: https://news.ycombinator.com/item?id=47816464 Points: 1 # Comments: 1
https://update.code.visualstudio.com 是不是挂了？我这里访问 503 了，导致我 VS Code 连不上 SSH 了 4 个帖子 - 3 位参与者 阅读完整话题
不是vscode + Copilot插件，是用ide自带的聊天框，个人觉得比插件好用，发送请求的时候带的UA是GitHubCopilotChat 觉得好用的点 可以自由配置API 2. 计划模式出来的方案挺适中的，真的需要二次确认的东西才会问你，其余会直接给出最优解 3. 编辑器定位能力很强，在一次聊天里面多次修改的文件，可以回溯修改的地方，比如文件A，在同一个会话里面的第一次对话里面修改了 100-120行，第一次修改了110-180行，你回去第一个对话那里的话，可以看到是改了100-120行，即使没有git也可以回溯的（当然还是建议佬友用git）对于我这种vibe coding同时也会看代码的人是福音 2 个帖子 - 2 位参与者 阅读完整话题
As a regular vibe coder, I came to really like claude-devtools for the level of observability it gives into tool calls, context allocation, and token consumption. But, I'm also a visual learner and the dialogue-style flow was not cutting it for me, especially when it came to system design. So, I went and built Centrality which combines some of my favorite features of claude-devtools with my own needs for codebase visualization. It shows you: - A graph of your codebase and which files have been touched - Detailed views of tool calls - Context window summarization - API cost broken down per message and per session - Where the session took place in your git log You can also use it to: - Resume existing Claude Code sessions (macOS and Windows) - Open focused files directly in your IDE - Connect to remote Claude Code sessions and codebases via SSH It's for anyone who vibe codes but still wants some insight into what's happening under the hood, and you need to see something to really understand it. I enjoy using Centrality as a companion tool for my own projects, and I hope you do, too! Comments URL: https://news.ycombinator.com/item?id=47788715 Points: 1 # Comments: 0
Article URL: https://github.com/rccyx/lookas Comments URL: https://news.ycombinator.com/item?id=47783528 Points: 2 # Comments: 1
Article URL: https://aiagentsbuzz.com/tools/rag-chunking-playground/ Comments URL: https://news.ycombinator.com/item?id=47778880 Points: 1 # Comments: 0
Inspired by karpathy's US job market visualizer[0], I started to dabble with the idea of building live dashboards for certain job markets, starting with quant finance. I extract the career pages of pretty much every major quant firm and classify each posting with a lightweight LLM ETL pipeline. The data is updated daily and the full dataset is available as SQLite for anyone who wants to do their own analysis. [0] https://karpathy.ai/jobs/ Comments URL: https://news.ycombinator.com/item?id=47770792 Points: 1 # Comments: 0
Article URL: https://davkap92.github.io/crowdscale/ Comments URL: https://news.ycombinator.com/item?id=47770704 Points: 1 # Comments: 0
Built a trace view to see OpenClaw LLM / tool / subagent calls and debug it. Comments URL: https://news.ycombinator.com/item?id=47769889 Points: 1 # Comments: 0
Hi HN! I've been using kitty for a while but yesterday i decided to switch to ghostty and i realized that i would need tmux to manage my panes if i wanted to get the grid as i wanted So i made the reasonable thing: built a visualizer for the layout so i can just copy the setup and drop the `.sh` wherever i need I probably missed a few thing in this but it's my first day with tmux any feedback would be absolutely amazing Demo: https://tmux-grid.itzami.com Repo: https://github.com/ItzaMi/tmux-grid Comments URL: https://news.ycombinator.com/item?id=47763748 Points: 1 # Comments: 0
Our AI Native IDE, 6digit studio, has a new Big Picture Mode visualization layer, CORDIAL, meant to be possible to use at a "distance", making you feel just a little bit more like Tom Cruise in Minority Report. Comments URL: https://news.ycombinator.com/item?id=47758969 Points: 4 # Comments: 2
Hi HN, I’m an amateur naturalist, and I couldn't find good visual content to study for animal/plant taxonomy. Standard text-based flashcards don't work well for visual identification. So, I built a visual spaced-repetition engine specifically designed to drill taxonomy using perceptual interleaving (showing you visually similar species back-to-back to train your eye). The stack: SvelteKit / CDK (S3) / Fallback R2 / Postgres Could probably use some better optimization but it works well enough. It uses a customized implementation of the FSRS (Free Spaced Repetition Scheduler) algorithm adapted for image-heavy visual drilling. The hardest part is building out the curated image database. There is planned content for many more species coming soon! The platform is currently in a 100% free beta. Would love some feedback, advice, etc if you have time! https://species.app Comments URL: https://news.ycombinator.com/item?id=47750352 Points: 3 # Comments: 1
Most companies deploying AI agents are accidentally building organizations. You start with one agent. It gets overwhelmed. You add more. They start routing to each other based on what works. Repeated behavior hardens into structure. Someone introduces an orchestrator to bring order. Some agents never get the memo. Some lose context when they get replaced. The orchestrator doesn't know what it doesn't know. This is what is happening in most engineering organizations right now So, I built an interactive visualization that walks through how this happens in six acts, from a single agent to a full emergent org chart. The visual starts center-out and transitions to a top-down hierarchy as structure forms. Failing agents flicker. Connections break. The orchestrator arrives and things look better than they are. The point of the piece is that the org chart your engineers could draw and the org chart that is actually operating are not the same document. Teams have the tooling to observe individual agents. Nobody has the layer that tells you what the system as a whole has decided, committed to, and authorized. Built with canvas, IntersectionObserver-driven scroll, and a layout interpolation between radial and tree positioning that transitions across acts. Has anyone here has hit the governance wall with agent systems in production and what it actually looked like when things went wrong. https://jointherevolution.today/emergence Comments URL: https://news.ycombinator.com/item?id=47736568 Points: 3 # Comments: 0
I'm trying to get into Gastown, and now Wasteland is kind of breaking my mind. I looked into what kind of data was being published and found that I could just read the public dolt data from dolthub. I envisioned it all as a game so I vibe-coded this isometric view of what's going on. The process of trying to refine this to show actually useful things going on really helped my understanding. You can't actually perform any actions, just visualize the data. I think Steve mentioned that people were working on turning Wasteland into a game, so maybe this already exists but I learned something making it. Comments URL: https://news.ycombinator.com/item?id=47734804 Points: 2 # Comments: 1