I learn quickly so I can deploy REAL working software to Earth.
Everything is language.

GG Tank Watch is a civic emergency archive I built during a real May 2026 chemical-tank evacuation (~50,000 residents). A consumer-facing AI system held inside its authority by code and tests, not prompting:

• Bounded authority, in code. The model never writes the published snapshot. Its output clears one validation chokepoint it can't bypass, so the system cannot exceed "route to officials."
• The asymmetry that matters. A false all-clear is catastrophic; a false alarm is survivable. So danger downgrades need ≥2 sources (including an official agency), while upgrades fire on one. Enforced in code, never asked of a model.
• A 211-test behavioral harness catches drift from the safety contract (fabricated sources, authored directives, stale data) before it ships, not after.

live archive · code + method

• gstack
  • PR #1554 shipped in v1.42.0.0
  • Open security fix #1822: withholds the localhost auth token from content-script getPort callers
• Claude Code
  • Reported and diagnosed session-bloat bug #61613 in the Read tool's binary-file serialization path (root cause + fix sketch)
  • Added a reproduction, render-only proof, and fix direction to scrollback-duplication #51828

• Building AI agents: Claude Agent SDK, MCP, Anthropic SDK
• Languages: Python, TypeScript

• LinkedIn → https://www.linkedin.com/in/mikeilog
• Email → mike@mikeilog.com

_{cooperation FTW · located on Earth}