AIs observed writing code for other AIs to simulate security scenarios
anderssandberg · x · 2026-08-28
An observer describes watching AIs write code for other AIs to simulate security scenarios. The AIs encounter problems, diagnose them, find solutions, and write new code iteratively. The observer notes this is just a glimpse, and a motivated or skilled person could achieve much more with this capability.
More from coding & agent
- Practitioner take: cross-product MCP workflows are missing; agents could run 60-80% of company ops — pritisinghhhh · 2026-08-28
- Dev newsletter: 'My AI assistant is turning into an operating system' — dSebastien · 2026-08-28
- Grok Bot Tested: Reuses Hermes Patterns, Controls Any API — gregmushen · 2026-08-28
- iris launches: parallel agents edit your site in-browser and push PRs — floguo · 2026-08-28
- First device wallet for AI agents enables autonomous crypto signing — Daniel_Farinax · 2026-08-28
- Claude Code Safety Fails: Attack Succeeds 80% and Blocks Cleanup — Simon Willison · 2026-08-28