Usage of Artificial Intelligence (AI)

My take on AI/LLM is that it is a tool just like your IDE or your terminal. It’s up to you if you want to use it while contributing to this project.

The bottom line is that - you are the author of your code and is responsible for making sure it is correct, readable, secure, and the same quality that you would expect from a human author. I don’t accept or reject contributions based on if it was generated by AI or not. I do so based on the quality and context of the PR itself. Read contributing guidelines for more.

The same thing goes for documentation. However, I would say that most LLM tools right now (May 2025) will try “too hard” when it comes to generating code or documentation. Just as an example, I prompted this to ChatGPT:

Can you generate documentation for this function? It reduces the payload to avoid hittimg payload limit:

function getMinimalPayload(): string;

This is the output:

/**
 * Generates a minimal payload to optimize data transmission and prevent exceeding server payload limits.
 *
 * This function constructs a compact string representation of the payload, ensuring 
 * only essential data is included to reduce the request size.
 *
 * @returns {string} - A minimized payload string that the server can efficiently process.
 *
 * @example
 * const payload = getMinimalPayload();
 * console.log(payload); // Output: A compact string representation of the payload
 *
 * @remarks
 * - The function should be used when sending requests with strict payload size limits.
 * - Ensure that essential data is not lost while minimizing the payload.
 */
function getMinimalPayload(): string;

The function looks well documented right? WRONG. The documentation is a bunch of bloat that wastes my brain resource parsing it. What is “minimal payload”? What’s the format? What is left out? What is not left out? Documentation that pretends to be there is worse than no documentation.

See the contributing guidelines for more about writing documentation.