In this Halloween edition of Rubber Duck Radio, hosts Tim Williams and Paul Mason dive into the intricate world of AI in software development. Discover how context management, legacy code, and the high cost of training large language models are shaping the developer experience. The duo explores the potential of LoRa training, the pitfalls of multi-agent environments, and the future of AI with MCP-style APIs. Tune in for a mix of humor and deep insights as they tackle the challenges and opportunities of integrating AI into real-world projects.