Why it matters
Claude is capable of long horizon tasks. In this talk, we'll share lessons learned about building agent harnesses for reliable and secure long-horizon work. This include decoupling the brain and hands, self-verification, self-learning, and design for evolving agent harnesses. ### Lance Martin Member of Technical Staff
My takeaway: Claude for Long-Horizon Tasks — Lance Martin, Anthropic is an agent-security signal. The practical read is that autonomy, memory, tool permissions, and third-party integrations are the control surface that needs threat modeling and monitoring.