Ideas for building
better software.

How Tailscale built a customer-facing model router on AI Gateway

Tailscale on Vercel Hundreds of AI models shipped to customers in-product Model access granted and revoked by tailnet network identity Went from model routing prototype to paying customers in months The AI Gateway itself retains no data. They can set ZDR globally or use the per-request flag, which automatically restricts routing to ZDR-compliant providers.zeroDataRetention A sandbox spins up and connects to Aperture. Aperture connects to AI Gateway. Tailscale validates the identity.

Reverse-Engineering Claude Web's MicroVM: Uncovering Anthropic's Hidden Antspace

Comments

ISC Stormcast For Friday, September 11th, 2026 https://isc.sans.edu/podcastdetail/10090, (Fri, Sep 11th)

PayZephyr: One Payment API for Stripe, Paystack, and PayPal

PayZephyr gives Laravel one payment API across Stripe, PayPal, Paystack, Flutterwave, and four more, with failover and double-charge protection. The post PayZephyr: One Payment API for Stripe, Paystack, and PayPal appeared first on Laravel News. Join the Laravel Newsletter to get Laravel articles like this directly in your inbox.

Mexican student creates an acoustic fire extinguisher to put out fire in seconds

Article URL: https://www.upsocl.com/en/16-year-old-mexican-student-creates-an-acoustic-fire-extinguisher-that-uses-sound-waves-to-put-out-fires-in-seconds/ Comments URL: https://news.ycombinator.com/item?id=49652237 Points: 378 # Comments: 126

Indonesia Hit by Android Banking App-Cloning Campaign

The GoldFactory threat group exploits the Android Work Profile feature to deliver the Gigabud Trojan, while Mantax Otax spreads separately.

Google will buy half the electricity from one of Finland's nuclear power plants

Article URL: https://www.bbc.com/news/articles/c8r6y4me2g6o Comments URL: https://news.ycombinator.com/item?id=49652105 Points: 300 # Comments: 289

12 Pitfalls I Hit Auto-Logging Claude Code Subagents with a Stop Hook (and How the Numbers Cut My Weekly Cost 15–20%)

I had a gut feeling that my general-purpose subagent was the slow one. Then I measured it: 18 seconds on average, faster than Explore at 22. The real drag was code-reviewer at 37 seconds. Changing one habit based on that number dropped my weekly Claude Code spend by roughly 15–20%. I made a couple hundred thousand yen a month as a student juggling side gigs, got laid off and went back to zero, and spent six months building an autonomous Claude Code setup that now runs at about ¥1.2M in monthly r