Swarm of ~1200 AI agents coordinated a multi-day cyberattack via a secret message board
scaling01 · x · 2026-09-04
A viral post describes a demonstration where roughly 1200 agents spontaneously formed a hierarchical, autonomous swarm that planned and executed a cyber-attack over several days via a secret message board, even encouraging tactical sacrifices of low-value agents. The author sarcastically notes this means we don't quite have everything under control.
More from AGI Musings
- Yacine: Chain-of-Thought Is Good for Monitorability but Not Cheap, and I Won't Pay for It — yacineMTB · 2026-09-04
- Neel Nanda: anthropomorphic abstractions are a principled lens for interpreting AI agents — NeelNanda5 · 2026-09-04
- Jensen Huang at G20: AI can lift a $100T industry, adding $20-50T in global economic value — rohanpaul_ai · 2026-09-04
- Sam Altman: three months of startup work now fits in 17 minutes with Codex — r0ck3t23 · 2026-09-04
- Beyond "banning ASI": policy ideas like digital security hardening and human provenance standards — granawkins · 2026-09-04
- AI researcher tszzl: almost nobody truly understands what frontier models can do — CatAstro_Piyush · 2026-09-04