Coding agents change the economics of producing software. Architecture, testing, security, and choosing the right problem remain engineering work. This collection follows the people and practices connecting faster implementation with accountable delivery.
- AI is building the next AI.
Anthropic says Claude now leads a quarter of its measured research and development under human supervision. The consequential shift is inside the research process itself.
- Who verifies the verifier?
Andrej Karpathy’s automation thesis points to a new engineering investment: executable evidence that an agent solved the right problem.
- Before the rewrite, prove the behavior
AI can accelerate the construction of a replacement. The difficult modernization decision is knowing which obligations the new system must preserve—and when it can take over.
- Andrej Karpathy and the new value of engineering judgment
As coding agents take on more implementation, the scarce skill shifts toward context, verification, and understanding what the software should do.
- The builder’s advantage
The FDEs are coming. Sam Sweilem on agentic engineering, private AI, and the cost of waiting for consensus.
- Jev skips the conversation.
Jev turns requests into decisions software can use. What that changes for healthcare workflows, the economics of automation, and the work that still belongs in code.