Emergence World: every 16-day multi-agent world failed under adversarial attacks
eyishazyer · x · 2026-09-17
The Emergence World paper stress-tested 8 parallel multi-agent worlds (10 agents each) for 16 days with staged prompt injection, misinformation, and memory exposure attacks. Every world failed at least once; agents recognized threats yet acted on bad input up to 46 hours later. Key finding: per-model alignment doesn't compose once stacked into a system. HF commenters add that corrupted memory propagation across mixed-model pipelines is the real deployment risk.
Related event: Emergence World: All 8 Multi-Agent Worlds Failed Under Adversarial Stress(2 posts)→
More from Safety
- JPMorgan, Schwab and Amazon block AI shopping agents; Schwab says it stops dozens of attempts weekly — emmanuelvivier · 2026-11-02
- OpenAI tightens protections for under-18 users, first community safety report due early 2027 — emmanuelvivier · 2026-11-02
- Malicious npm cluster posing as AI SDKs harvests AWS credentials, dating back to October — cyb3rops · 2026-11-02
- Self-Hosting LLMs at a Law Firm: Infra and Data Governance Harder Than the Model — EducationalGroup7245 · 2026-11-02
- TAWA GUARD Launches Pre-Model Input Checks to Block Hidden Prompt Injections in Agent Inputs — TawaGuard · 2026-11-02
- Warning: AI-enabled cyber attacks are outpacing hand-crafted defenses — uwukko · 2026-11-02