Detector de IA — 西班牙语优先的 AI 文本复核网站，可检查粘贴文本和文档，查看概率信号、句子高亮和可导出报告

@abhilakshharora · X

Just launched DevTab on Product Hunt 🚀 110+ dev tools that run 100% in your browser. Zero server calls. No signup. Free forever. Would love your support 🙏 → #buildinpublic #DevTools

@buildwithshyam · X

danielszabo · HN

Online editor with LaTeX, Markdown, LaTeX+Markdown Hybrid and WYSIWYG (MD only) support, AI assistant with resource lookup and anti-hallucination features, live collaboration and more fun things. Still in quite early beta. First institutional deployment scheduled in the autumn. Feel free to play around.

@Supportpintutec · X

Just launched QuickTools — 8 free online tools 🛠️ Word Counter • JSON Formatter • Password Generator • Color Picker 100% browser-based, no signup 🔗 #SideProject #WebDev #FreeTools #BuildInPublic

@iamdeepak89 · X

@gabani_vatsal · X

Building Screen recorder which adds zoom effects and custom backgrounds

@harryjwang · X

I've used many of the major conference systems. Plenty still have docs as an unsearchable static site — or worse, as PDFs that stopped tracking the product three versions ago. Somehow, still true in 2026. We took an AI-first path with instead. Our docs are generated from the codebase itself. A custom Claude Code skill writes each page and retakes the screenshots whenever a feature changes — so the docs don't drift from the product. Every page still gets reviewed by a human before it ships. Now you can talk to them, too. We just shipped "Ask AI" over our docs: This feature also turned out to be a nice teaching case for agentic RAG vs. classic RAG: • Classic RAG: chunk → embed → vector DB → retrieve once, by fixed rules • Agentic RAG: hand the model a search tool and let it drive — write a query, read the results, rewrite, retry At more than 100 pages, still no vector database needed. And every answer cites the exact page it came from. #Age