Context Rot
Chroma's empirical study showing model performance degrades as input context grows, even well below the window limit. Heavily cited in the context-engineering debate.
Articles
- Effective context engineering for AI agentsAnthropic's reference piece on context engineering — what to put in the window, what to leave out, and why. The canonical framing for the topic.Read Later
- The Bitter LessonRich Sutton's classic essay: general methods that scale with compute beat hand-engineered knowledge. The lens behind most agent-harness design debates.Read Later
- We removed 80% of our agents' toolsVercel on why fewer, better tools beat a sprawling toolset — fewer tokens, less confusion, better task completion. Contrarian and concrete, directly relevant to CX agent design.Read Later