Right, I'm saying "model training" is vague enough that I have no idea what Claude actually does with this document.
Edit: This helps: https://arxiv.org/abs/2212.08073
Edit: This helps: https://arxiv.org/abs/2212.08073
At a high level, training takes in training data and produces model weights, and “test time” takes model weights and a prompt to produce output. Every end user has the same model weights, but different prompts. They’re saying that the constitution goes into the training data, while CLAUDE.md goes into the prompt.