JMJoshua Markerinengineering.fractional.ai·Feb 5, 2025 · 2 min readDo what I meanTests are crucial to reliable code. I’ve found I do a better job writing tests if I think of them as specifications and write them before I write code. I find I think more clearly about what I want to00
JMJoshua Markerinengineering.fractional.ai·Oct 30, 2024 · 6 min readCustomizing Cursor's code generation and personalityOne of our rules at Fractional.ai is “overuse AI”. This is a bit tongue-in-cheek, but what we mean by it is that even within our own work, we occasionally suspend disbelief and give an AI tool a chanc00
JMJoshua Markerinengineering.fractional.ai·Oct 8, 2024 · 6 min readInsisting On Known Knowns: Using Evaluators to Drive ReliabilityLLMs are heuristic and opaque. Without the ability to selectively measure elements of correctness, you can’t be sure your system is behaving. Every GenAI project starts with a phase of looking at indi00
