The Optimal Amount of Slop is Non-zero
Doug Slater
A developer argues that the appropriate level of code review for LLM-generated software should match the risk level of that software, not be uniformly strict or loose. The decision depends on factors like how long software must work, how many people it affects, and how badly failures could harm users or the organization. The author ships unreviewed LLM code for personal tools with limited distribution but conducts review for mission-critical or widely-distributed software, and notes that optimal rigor varies based on whether you prioritize speed, business value, learning, or ethical concerns.
Why it matters
Software requires different levels of verification depending on its use case, with casual software having loose quality constraints while business and mission-critical software requiring higher scrutiny. The amount of permissible AI-slop decreases as the risks of the software failing increase.