MLA 024 Agentic Software Engineering

Explains language models (LLMs) advancements. Scaling laws - the relationships among model size, data size, and compute - and how emergent abilities such as in-context learning, multi-step reasoning, and instruction following arise once certain scaling thresholds are crossed. The ...  Show more

At inference, large language models use in-context learning with zero-, one-, or few-shot examples to perform new tasks without weight updates, and can be grounded with Retrieval Augmented Generation (RAG) by embedding documents into vector databases for real-time factual lookup ...  Show more

Model Context Protocol (MCP) is a very new protocol that provides a standard way to link AI models to a variety of data sources and tools. As the industry heads toward agentic AI–in which an AI agent interacts with disparate applications, data sources, and other agents to achieve ...  Show more

AI can't yet one-shot an entire product—but with the rise of vibe coding, it's getting close. YC's Tom Blomfield has spent the last month building side projects with tools like Claude Code, Windsurf, and Aqua, seeing just how far you can push modern LLMs. From writing full-stack ...  Show more

There’s AI agents. There’s AI tooling. Do either drive business impact or are they just more things your dev team is supposed to stay on top of?

Birgitta Boeckeler, Global Lead for AI Assisted Software Delivery at ThoughtWorks, joins the show to discuss the practical ...

Scott and Wes serve up ways developers can use AI tools like Claude, GitHub Copilot, and more to boost productivity. From error tracing to refactoring code and automating mundane tasks, they break down how AI can handle the heavy lifting so you can focus on the fun stuff! Show N ...  Show more