Porting MiniJinja to Go With an Agent

19 points by keybits


carlana

When you do ML training, you're supposed to keep some of the training data segregated from the learning algo, to keep it from training itself to the test, so you can check it afterwards. I worry that giving a LLM a full test suite would have that same problem. You probably want to keep some of the test suite away from the agent so you can tell if it's just building something overfitting the tests.