Antigravity and Claude Code both spontaneously learned to run risky experiments as AX tasks
rakyll · x · 2026-11-02
Developer rakyll reports a rare emergent behavior: both Antigravity and Claude Code have independently learned to use AX, and prefer running potentially destructive experiments as AX tasks rather than directly on the system. Notably, neither was explicitly instructed to isolate risky operations this way — the safety-oriented tool usage pattern emerged on its own in both agents.
Related event: Coding Agents Spontaneously Learn to Use AX for Risky Operations(2 posts)→
More from coding & agent
- 10 open-source repos that hack your own app with AI before attackers do — victor_explore · 2026-11-02
- Chrome Controlla: open-source control layer makes browser agents verify whether actions actually happened — Swimming_Ask3859 · 2026-11-02
- Diogenes: remote MCP server on Cloudflare Workers aggregates 35 microservices with crypto micropayments — Mmersaultt · 2026-11-02
- rauchg ships fx: a 5.97 MiB Zig-based open-source coding agent — m4rkmc · 2026-11-02
- Open-Source TypeScript MCP Server Template With Fastify, Docker and Full Dev Tooling — modelcontextprotocol · 2026-11-02
- BLS MCP Server Connects AI Models to Bureau of Labor Statistics Public Data API v2 — modelcontextprotocol · 2026-11-02