Ephemeral Testing: A New Way to Validate Software with AI

Daniel Lemire proposes ephemeral testing: instead of directly testing a core library, you have an AI agent build a throwaway application on top of it and test that. A clean API and stable invariants let the agent succeed quickly; hidden state or poor docs produce failures. Those failures reveal the quality of your foundation, not the agent. Lemire has used this trick on his own projects.