Today’s thread is practical AI engineering: agent browsers, safer code edits, MCP stateless connections, and the abuse economy around cheap LLM tokens. There are also solid reads on proof automation, HyperCard-style tools, and small but useful desktop automation.
Anthropic closes a $65B Series H at $965B post-money and ships Opus 4.8. SQLite-as-workflow-engine and the MCP-is-dead thesis dominate HN. AWS Kiro Web, .NET MAUI on CoreCLR, and a Zig build system rewrite round out the day.
A telling Thursday on HN. Zed 1.0 lands with the day’s highest score (1319 pts, HN #2) — but the #1 slot belongs to a GitHub issue inside anthropics/claude-code: a config file called HERMES.md, an internal A/B experiment, double-charged a customer ~$200 and Anthropic refused the refund (836 pts). HN #13 ‘We need a federation of forges’ (488 pts) keeps yesterday’s Ghostty-leaving-GitHub thread burning. AI: Mistral Medium 3.5 ships remote agents (HN #24). Security double feature: Copy Fail / CVE-2026-31431 (HN #3) and Ramp’s Sheets AI exfiltrating financials via prompt injection (HN #9). Japan’s Zenn delivers two strong Claude Code field reports — LayerX’s ‘ccgate’ auto-approves 97% of permission prompts; Finatext warns against handing Google accounts to AI agents. China’s V2EX is consumed by Xiaomi’s MiMo Token Plan.