alt Hacker NewsAfter I stopped letting Claude run tests, my token usage went from "gone by Wednesday" to "what can I automate this Saturday so my tokens won't go to waste".
After I stopped letting Claude run tests, my token usage went from "gone by Wednesday" to "what can I automate this Saturday so my tokens won't go to waste".
What is the reason for this? Surely running tests by itself isn't necessarily token-expensive? And it provides cheap feedback for the agent: to see whether they're breaking things.