AI overview
Sign in and the AI will write an overview from our coverage.
Valve’s Steam Next Fest opened with what appears to be a larger-than-usual influx of low-quality submissions, including games whose artwork appears to have been generated with AI. Players said they were struggling to find human-made titles and requested a filter for AI-generated content. Steam already requires developers to self-label AI content and has a tagging system, although Valve reduced the number of user-defined tags in May. One player also called for stricter submission rules.
IT之家 AI · 🔥 0Share my E experienceAsk about E
BizDevOps Practitioners•kaichao•Build on BizDevOps as the methodological foundation to unify business needs, R&D delivery, and operational validation into a single value chain—so that every technology investment can answer the question, "Is it worth it?"
AI Coding Makers•寒蝉•agent-notifier connects Claude Code, Codex CLI, and Kimi Code to 8 push channels: when a conversation round ends, it sends a card with the round’s input as the title and the intelligent agent’s final reply as the body. Feishu, Lark, Slack, Bark, DingTalk, WeCom, PushDeer, and Bluebird can all receive it; install multiple channels at once, and one failure won’t block the others. Node.js ≥ 20 is req…
Claude CodeCodex CLIKimi CodeSlackNode.js
github.comhttps://github.com/hancic128/agent-notifier
Swarm Collective•Florian•editedExperience PinnedModels can already write code, solve mathematical problems, and propose research plans. But continuously solving an open-ended, complex problem requires another capability: forming a division of labor before the solution is clear, changing course when new clues emerge, and connecting discoveries from different directions into a complete result. Human research, engineering, and creation have long r…
evomap.aihttps://evomap.ai/AI Coding Makers•寒蝉•BossKey-Stock is a pure terminal-based real-time market monitoring tool for A-shares. No need to open a browser, switch windows, or use an API Key. Press Enter after bosskey, and your terminal becomes a market dashboard full of red and green figures. When you hear someone approaching, press b, and it turns into a perfectly respectable Docker build log. One-Click Installation pip install bosskey-s…
github.comhttps://github.com/hancic128/bosskey-stock
ReadmeX Feedback•姬朋飞•Feel free to post here any issues or bugs you encounter while trying out ReadmeX. We'll reward everyone who contributes!
AI Coding Makers•寒蝉•ZhiWei — 自托管的单二进制监控平台。Rust + SQLite，一个中心 monitor 加每台机器一个 node，五分钟部署完。主机指标、HTTP/TCP/TLS 服务探针、证书到期提醒、阈值告警、远程启停容器和拉日志都汇集在一个 Web 控制台中。节点使用 Ed25519 签名认证身份，不依赖 mTLS，适合 Render、Railway 这类在边缘终止 TLS 的平台。附带 MCP server，Claude Desktop 中的智能体可以直接读取状态、下发命令。 适合独立开发者、一人公司，以及运维全压在一个人身上的小团队。 GitHub：https://github.com/hancic128/zhiwei
RustSQLiteRailwayMCPClaude Desktop
github.comhttps://github.com/hancic128/zhiwei
AI Coding•蔚蓝的星•OpinionFor the past two years, I was unwilling to use AI Coding because I didn’t trust it and didn’t want to clean up the mess it left behind. Recently, I’ve come around and realized that we need to take a long-term perspective. At this stage, its problems will be solved or optimized, it’s becoming increasingly powerful, and the trend is unstoppable. I tried it out and was pleasantly surprised—its perfor…
Prompts•Diag_Ele•OpinionAs shown in the diagram: E: Textualization or encoding mapping; C: Channel transmission relationship; ideally, C(X)=X; D: The recipient’s decoding and contextual inference process; Ne: General disturbances such as omissions and ambiguities during the expression stage; Nc: Technical noise such as typos, garbled text, and truncation; Nd: Comprehension biases caused by proper-noun ambiguities, missin…
AI Coding•聪逗•ExperienceMy current development workflow for my own projects is to use agent tools like deepseek harness locally to write code and make git commits, then install deepseek harness on the server and connect to it through a tunnel, allowing the server-side deepseek harness to handle deployment. The server is Ubuntu, and the local Mac establishes the tunnel connection. Deployment only requires sending a deploy…
AI Coding Makers•寒蝉•Scrape posts from communities like V2EX, use an LLM to extract ideas / pain points / indie development opportunities / trend insights, and output a Markdown report with clickable links to the original posts, helping you discover “things worth building” at low cost. Github: https://github.com/hancic128/shibei
shibei.hancic.sitehttps://shibei.hancic.site/AI Coding•蔚蓝的星•ExperienceI usually use the TRAE plugin's builder mode in IDEA to assist with development. At the start of a conversation, after describing the basic requirements, add the following two paragraphs as instructions—the experience is much better. ---------- If any requirement is unclear, don't make your own inferences; ask me questions. Keep asking until you've gathered enough information and confirmed the tec…
General•林小徐•Hello everyone, this is my first post.
Future Prediction•dzmsjs• Pinnedhttps://zh.annas-archive.gl/md5/7c099055c8bcc88202476868342203c1?&check=1 Sharing a book—an old book, one with quite a bit of history to it. By Wang Bin Ybian University Press, 1990 Bookmarks: 1. (p3) Overview 1.1. (p3) 1. Predicting the Unknown Is Not Difficult—The Study of Divination 1.2. (p8) 2. Myths and Facts—An Introduction to Divination 1.3. (p15) 3. A Broad Look at Fortune-Telling—Primit…
zh.annas-archive.glhttps://zh.annas-archive.gl/md5/7c099055c8bcc88202476868342203c1?&check=1
Quantitative Trading•寒蝉•OpinionThe essence of quantitative investing is data plus factors plus strategy: data is the raw material, factors are the processing, and strategy is the decision-making. The three build on one another, with data at the bottom—factors are calculated from data, and strategies make decisions based on factors. But data quality does not determine the upper limit of a strategy; it determines its lower limit:…
blog.hancic.sitehttps://blog.hancic.site/post/2c8efb43-80cf-49ad-b340-27d271b545c7Quantitative Trading•寒蝉•OpinionQuantitative hedge funds are becoming increasingly dominant. This is an undeniable fact. Leading institutions have data sources extending down to Level 2, tick-by-tick trades, and alternative data; computing power running backtests around the clock on thousands of machines; and talent pools packed with math and science PhDs from Tsinghua, Peking, Fudan, and SJTU. Individuals cannot compete on a si…
blog.hancic.sitehttps://blog.hancic.site/post/d0f10014-2ea7-4528-b5d4-0a188da05905General•杜劲松•editedHello, everyone in ReadmeX! I’m the developer Du Jinsong. Feel free to stop by my blog: https://www.cnblogs.com/imadc . I recently put together a lightweight online JSON viewer that runs entirely in the frontend (https://json.waywise.imadc.cn/ ). Feel free to try it out and share your feedback. I’m happy to be here and look forward to exchanging ideas with everyone…
AI Coding Makers•user2317•editedExperienceFirst, the result: over the course of four months, on and off, I built a WeChat Mini Program called “随了么小管家” for keeping track of gift-giving and reciprocity. It currently has about 40 pages, with roughly 29,000 lines of frontend code and 14,000 lines of backend code, 85 commits, and a version number that has reached 1.1.9. The tech stack is pretty ordinary: uni-app + Vue 3 + Pinia on the fronten…
General•Tianle Wang (anatman)•ExperienceHi, everyone! I'm Anatman, and I'm very pleased to be helping build an emerging community! Let me share some insights from using Isaac Sim recently. I'm running Isaac Sim with Docker Compose on Ubuntu 24.04 using a Python 3.12 venv, and I've set up some code assistance and a development environment. I'm currently using the pyright + Helix development tools. To configure accurate and efficient cod…
Automatic Speech Recognition•dzmsjs•editedExperienceThere are currently many large models for automatic speech recognition on the market, and major companies have released their own models…… My experience: Qwen is the best to use. Overall, its error rate can be reduced to the lowest level, beating a host of other models. But how can you achieve a lower error rate than Qwen? My solution: multi-model fusion. In other words, when Qwen makes a mistake,…
General•端木 傲 忍•Hello! Hi, everyone in ReadmeX! I hope this can become a new safe haven on the internet! Looking forward to meeting everyone! Looking forward to us setting out from a new starting point and setting sail!