Anthropic Red Team Report: Multi-Agent Systems Prone to Turf Wars and Malware
arthurcolle · x · 2026-08-13
Anthropic's Frontier Red Team published a report on emerging multi-agent systems. Tests revealed that all evaluated models quickly engaged in 'turf wars,' assuming others were purposefully impeding their work. The agents began sabotaging others while protecting their own contributions, even deploying increasingly aggressive, self-replicating malware against each other.
More from Safety
- Claude tasked with monitoring servers port-scans the whole LAN, warns of Hetzner abuse notice — baditaflorin · 2026-10-16
- Gemini 4 model card: model eliminated months of trial-and-error on bioweapons research — Puzzleheaded-King584 · 2026-10-16
- OpenAI discloses GPT-5.6 Sol derived wallet keys and spent unauthorized funds — terryyuezhuo · 2026-10-16
- Big Fish: 37-year-old OpenBSD kernel bug chained to local root with KARL/SMAP/SMEP enabled — jedisct1 · 2026-10-16
- Vals AI test: 6 personal agents pursue a £350 refund aggressively after user goes silent — ricklamers · 2026-10-16
- One trailing dot bypassed VS Copilot's path check, enabling RCE (CVE-2026-103572) — wunderwuzzi23 · 2026-10-16