Excellent post. People always defend agentic/LLM-driven development by saying, "Well it's good enough", or "It works most of the time."
That may be tolerable for some user-facing app. But what if we start normalizing failures in the libraries, the infrastructure, and the compilers? Everything descends into a mess of unreliability, and that slows EVERYTHING and EVERYONE down.
Write tests first. Have agent iterate until they are satisfied.
The point is that it boils down to writing the tests correctly, regardless of who is implementing the actual code. Hand-written code without test coverage has the same problems as AI generated code.
adamddev1 · · focus · HN ↗
That may be tolerable for some user-facing app. But what if we start normalizing failures in the libraries, the infrastructure, and the compilers? Everything descends into a mess of unreliability, and that slows EVERYTHING and EVERYONE down.
psadri · · focus · HN ↗
The point is that it boils down to writing the tests correctly, regardless of who is implementing the actual code. Hand-written code without test coverage has the same problems as AI generated code.
wonnage · · focus · HN ↗
<a href="https://ravimohan.blogspot.com/2007/04/learning-from-sudoku-solvers.html?m=1" rel="nofollow">https://ravimohan.blogspot.com/2007/04/learning-from-sudoku-...
wartywhoa23 · · focus · HN ↗
Or have them rig the tests so that they always pass.
antonvs · · focus · HN ↗