Today’s picks focus on AI becoming infrastructure: model routing, language runtimes, reasoning-trace security, codebase retrieval, local LLM economics, and the everyday browser details that still shape developer work.
Three threads this morning. (1) The platform layer is paying down years of debt at once: VS Code 1.108 ships a preview ‘Agent window’ for running multiple coding agents side-by-side, the long-running Bun rewrite-in-Rust PR finally lands on main, Node.js 26 turns on Temporal by default, and Mojo 1.0 hits Beta. (2) Security and privacy are pushing back hard: HN’s #1 story (442 pts) is an owner physically removing the DCM and GPS from a 2024 RAV4 hybrid, #2 is a public stack-overflow PoC against Nginx, and the V2EX thread of the day is a manager discovering coworkers resold the company’s LLM gateway key. (3) Skills as an interface have a real day in the sun: obra/superpowers cracks the GitHub trending top 5, and a Zenn write-up of Claude Code vs Codex playing Othello with identical Skills (final: 56-8) is making the rounds.
HN’s top three slots are all AI trust stories: Claude Code allegedly refusing or upcharging requests when commits mention ‘OpenClaw’ (865 pts); PyTorch Lightning hit by a Shai-Hulud-themed supply-chain attack (299 pts); Rivian shipping a real, vehicle-wide kill switch for cloud telemetry (331 pts). V2EX threads document a Gemini quality regression and a clean mihomo-via-Tailscale exit-node recipe. Publickey covers Node.js 26 enabling Temporal by default and Mojo reaching 1.0 Beta. Simon Willison ships a CSP allow-list iframe experiment and quotes Boris Mann’s deadpan: ‘11 AI agents’ is as meaningful as ‘11 browser tabs.’ On GitHub Trending, obra/superpowers — a packaging convention for Claude Code skills — keeps climbing.