Posts tagged security.

5 posts · all tags

DateTitleTagsMark
2026-10-27 Canaries for the attacks that leave everything running
An attacker can steal your API credentials while your application carries on working. Canaries can make some of that hidden activity visible.
security engineering ai
2026-04-11 The Future of Security Is an Open-Source Model That Detects and Acts on Threats
Anthropic's Glasswing is for enterprises with six-figure security budgets. The rest of us need open-source security agents that learn our systems and act autonomously.
ai security architecture
2026-04-08 Claude Code Running Claude Code in 4-Second Disposable VMs
Anthropic has an internal platform for running Claude Code in full-permission isolation. I built my own version with Firecracker MicroVMs, Go, and a $400 Ryzen box.
ai Go programming architecture
2026-04-05 Stealing NanoClaw Patterns for Web Apps and SaaS
Four architectural patterns from NanoClaw's tiny codebase that translate directly to production web apps and SaaS — credential sidecars, infrastructure-level isolation, polling loops, and Postgres as your message queue.
architecture security engineering
2026-03-23 NanoClaw's Architecture is a Masterclass in Doing Less
I pulled apart NanoClaw's 8,000-line codebase and found six architectural patterns that most SaaS teams should steal — credential proxies, container isolation as authorization, two-cursor message processing, and more.
ai architecture security