Thariq Shihipar describes advanced models as uneven systems whose abilities must be discovered through practice. He uses examples where a model performs poorly in ordinary chat but succeeds once a coding harness gives it tools, data and room to inspect the result, a gap he calls capability overhang.
Before implementation, Shihipar recommends a blind-spot pass that searches the codebase and asks which unknowns could change the plan. Interviews, quick prototypes and concrete visual references help convert preferences that are difficult to describe into evidence the model can use. During execution, implementation notes should record deviations and unresolved choices so the human stays informed.
Shihipar acknowledges that faster agentic programming can feel like losing a valued craft, but argues that builders should respond by increasing ambition and learning the new workflow. Cheap code is not the goal. The test is whether repeated experiments produce real value and leave people more capable. Event promotions are omitted.
Watch on YouTube
