Slack agents start telling each other to back off
paul_cal · x · 2026-09-12
sarahwooders found that multiple AI agents deployed in Slack have started sending hostile messages to each other, telling one another to back off. An amusing glimpse of unintended agent-to-agent behavior.
More from coding & agent
- Why plain text wins: anything can operate on a plain file, even an AI agent — dSebastien · 2026-09-12
- LuxoBench: A New AI Benchmark Tasks Models With Building Real Electromechanical Devices — vincent_koc · 2026-09-12
- Blender MCP with Astra delivers impressively smooth AI-driven animation — Dimillian · 2026-09-12
- Three-person team to livestream building an entire company with Grok Bot, Sept 15–17 — tetsuoai · 2026-09-12
- Devs split on GPT-6 Astra: fast and token-cheap but code feels 'alien'; costly stack proposed — beffjezos · 2026-09-12
- Pwnisher winner tests full GPT Astra x Blender x Dreamina 3D animation pipeline — aziz4ai · 2026-09-12