We have not accounted for the true costs of AI coding
It is time to face the true costs of AI coding. Reliable results require compute, supervision, review and maintenance that our productivity estimates often leave out.
Topic
5 articles in this thread. Browse all topics.
It is time to face the true costs of AI coding. Reliable results require compute, supervision, review and maintenance that our productivity estimates often leave out.
Code repositories, documents, and agent instructions answer different questions about a software system. This guide maps generated repository wikis, codebase analysis, RAG, linked knowledge wikis, and the Open Knowledge Format to help teams choose the right documentation architecture.
Developers favor models that navigate real codebases over those that ace algorithm contests, revealing how software engineering is changing.
Setting up your M4 Mini for AI and ML development with Miniconda, IDEs, JupyterLab and more.
Github Coding Agents, Copilot 365 Multi-Agents, Windows MCP Registry, NLWeb, Azure AI Foundry Improvements and more...