Tag
Andrej Karpathy states that 90% of Claude's mistakes stem from missing context, not model weakness, and provides a set of 12 rules that reduced error rates from 41% to 3% in experiments.
A personal reflection on the transformative potential of AI agents with persistent memory, arguing that context and workflow organization will become more important than the models themselves.
HydraPlus is an open-source memory and context layer for AI agents that uses a live knowledge graph, combining graph traversal, semantic search, and BM25 to provide persistent, secure, and self-managing context across multiple agents.
Comie.dev provides a production context for AI applications, integrating logs, databases, and error tracking.