Context is Infrastructure, Not InstructionsWhat teams gain when they govern AI context like a software dependency5d ago5d ago
The Turn as the Unit of QualityWhat makes iterative refinement productive, and when it starts to hurtMay 8May 8
The Capability-Reliability Split in Agent SystemsWhy frontier agents reach state-of-the-art on one run, and fail at the same task on the nextApr 30Apr 30
The Edge of the UnderdefinedThis is the final article in “The Meta-Engineer,” a three-part series examining how AI is reshaping the identity and skill set of software…Apr 23Apr 23
Don’t Vibe, ArchitectHow professionals work with agents, how context scales, and why orchestration is a transitional skillApr 16Apr 16
Context is the New CodeThis is the first article in “The Meta-Engineer,” a three-part series examining how AI is reshaping the identity and skill set of software…Apr 9Apr 9
Closing the Loop: How Human Corrections Can Make AI Systems Smarter Over TimeEvery day, thousands of domain experts in law firms, hospitals, and financial institutions review the outputs of AI systems and quietly fix…Apr 1Apr 1
Offline RL and the Data FlywheelHow production systems learn from logged data, and why dataset quality is the most underinvested layer of the RL stackMar 25Mar 25
Reward Design as ArchitectureWhy the reward function is the most consequential, and most overlooked, design decision in any RL systemMar 18Mar 18
Designing for Graceful Failure in Compound AI SystemsCompound AI systems, architectures in which multiple specialized AI agents collaborate to complete complex tasks, are becoming the dominant…Mar 11Mar 11
