Language modelsXataka
This is the 'prompt' that works best: the one that tells the AI how it should interact with you

The piece discusses how providing a consistent context through a prompt can improve an AI model's responses. It recommends instructions such as being concise, rigorous, not fabricating information, supporting claims with scientific articles, and avoiding agreement without justification.
Summary written by Kernelia from the original article by Xataka. The story and its rights belong to its author.

