标签：#hack

https://twitter.com/arnal_charles/status/2060009395107377282 , https://xcancel.com/arnal_charles/status/2060009395107377282 Paper: Formalizing Mathematics at Scale - https://arxiv.org/abs/2605.29955

Every week another "AI agent for X" launches. Email triage. Calendar coordination. Sales follow-up. PR reviewer. Slack monitor. Meeting summarizer. I've installed enough of them to see the pattern. Here's the dirty secret nobody mentions in the launch posts: These tools don't reduce your work. They multiply your notifications. Each AI tool is configured to be helpful by default. "Helpful" means: "I noticed this thing — here's a notification." Stack a dozen of those, and instead of one inbox to ignore you have twelve. The signal-to-noise ratio gets worse every time you add an AI to your workflow. The mainstream answer is "just configure each one." Sure. Spend four hours tuning notification settings every time you add a tool, and another four hours when one of them ships a "smarter notifications" update. That's not productivity. That's notification janitorial work disguised as setup. This is a structural problem. Not a configuration problem. The wrong question Every AI tool asks the same thing: "Is this important?" Wrong question. There is no objective "important." Importance depends on you, right now. A Stripe webhook is important when you're debugging a checkout flow. The same webhook is pure noise during a deep work block. A Slack message from your cofounder is critical at 11am Tuesday and irrelevant at 11pm Friday. The right question is: Is this urgent enough to interrupt me, right now, given what I'm doing? That's not a question any individual AI agent can answer. It's a layer above all your AI agents. None of them have the context. None of them know what the others are doing. None of them know how you're spending the next hour. So they all default to "I'll just send you a notification, you decide." Which is exactly the experience you have right now: drowning. What an AI firewall actually looks like I'm building that layer. It's called Klorn . Here's how it works in practice. Every signal — email, calendar invite, agent action, webhook, push from another tool — g

When Mozilla shut down Pocket in July 2025, I lost my favorite tool. Worse, none of the English alternatives (Instapaper, Readwise, Matter, Raindrop) had Japanese UI, and their article extraction was mediocre on Japanese pages. So I built one. It's called Readbox — Japanese-first, English-too, read-later as a PWA. Here's what I learned shipping it. The stack Next.js 15 App Router + TypeScript strict (no any ) Supabase (Postgres + Auth + RLS) Stripe (JPY + USD prices, locale-routed) Tailwind CSS Service Worker for PWA install + offline read Three things that bit me 1. Article extraction on Vercel serverless First attempt: Mozilla Readability + jsdom. Doesn't bundle on Vercel because of ESM compatibility issues and the 50MB serverless function size limit. I tried 6 approaches — Webpack externals, dynamic imports, edge runtime — none worked cleanly. Ended up using Jina Reader , which returns clean Markdown/HTML from any URL. Trade-off: third-party dependency, rate limits at scale. But it works today, and it's free. 2. Storing article body on-device I didn't want to host millions of articles' worth of HTML on Supabase (cost + privacy). Solution: extracted HTML lives in the browser's IndexedDB only (via Dexie); only metadata (URL, title, tags, read status) syncs to the server. Trade-off: cross-device sync of body content doesn't work seamlessly. Acceptable for a "read it later" workflow where you usually read on the device you saved on. 3. i18n routing — the silent sitemap killer For Japanese + English from one codebase: app/[locale]/ segment with /en prefix for English (default Japanese has no prefix, to preserve old URLs). Middleware detects cookie / Accept-Language and redirects accordingly. The gotcha (cost me a launch-day hour): middleware matcher excludes _next , api , image extensions — but if you forget .xml/.txt/.webmanifest , sitemap.xml and robots.txt get rewritten to /ja/sitemap.xml (which doesn't exist as a route → 404). Fix: export const config = { matcher

Hi HN, we’re open-sourcing ktx. It’s an executable context layer that makes agents reliable on your data stack. We built it after going through the experience of building production-grade data agents for dozens of companies. If you’ve also tried building them, or simply tried using Claude Code or Codex on your data warehouse, you’ll know that accuracy is the #1 issue. Agents are great at generating valid SQL, but it’s not always correct SQL. To cite a few examples of “agents gone wrong”: - Stale