Gray Swan relaunches red-teaming Arena contest for the AI agent era
jeremyakahn · x · 2026-10-20
Per an exclusive from Fortune's Jeremy Kahn, AI security company Gray Swan is relaunching its red-teaming Arena contest, updated for the era of AI agents. The competition invites the community to stress-test models and autonomous agents for security failures.
More from Safety
- Rising breaches track attacker AI adoption; the fix is relentless baseline controls — philvenables · 2026-10-20
- METR reviews Anthropic's Risk Report, sees low misalignment risk but key disagreements — CFGeek · 2026-10-20
- Reward misspecification in RL makes chain-of-thought unmonitorable, new safety research finds — johnhewtt · 2026-10-20
- CISOs Need Decision Support, Not Dashboards: What AI Security Tools Get Wrong — philvenables · 2026-10-20
- Anonymous audits of public MCP servers find read-only tools that can write and spend — Suncly_com · 2026-10-20
- 13,000-word essay: the AI-as-Normal-Technology view of loss-of-control incidents — random_walker · 2026-10-20