{
  "id": 757523,
  "title": "Let Them Write RFCs",
  "url": "https://urgent.news/2026/08/13/let-them-write-rfcs",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-08-13T10:48:29.000Z",
  "source": {
    "name": "Lobsters",
    "slug": "lobsters",
    "url": "https://ohadravid.github.io/posts/2026-08-let-them-write-rfcs/"
  },
  "original_language": "en",
  "account": "Here's my attempt at a report based on the provided source material:\n\nFor a complex project that exceeds my current expertise, I found myself spending hundreds of millions of tokens to create four versions of the same markdown file. This experience highlights the challenges of working on unknown problems, even with the assistance of large language models (LLMs).\n\nSome argue that tackling unfamiliar tasks without sufficient understanding is unwise. However, I believe that actively working on a problem is what leads to true comprehension. Yet, LLM usage can create a cycle where friction is minimized, allowing continued work without fully grasping the underlying concepts, potentially leading to misguided solutions.\n\nThe key insights that helped me navigate this issue were:\n1. Discarding early, incomplete implementations that didn't work well. Building bad drafts reveals crucial problems and accelerates learning.\n2. Employing LLMs to generate RFCs (request for comments) that articulate the problem, proposed solutions, and alternatives. This forces me to explain the problem and solution in a clear, concise manner.\n\nI posed the model with questions like \"Write an RFC about this problem and how to solve it. Keep it short, include good examples.\" By iterating on successive RFC versions (V1, V2, etc.), I consulted documentation and researched as needed until I had a solid understanding of the problem and confidence in the proposed ideas.\n\nAn RFC serves to clarify the problem, expose hidden assumptions, and guide the development process. However, the final code implementation may still fall short of expectations. In such cases, I would review the diff, compare it to the RFC, and either revise the code or start anew with a new RFC.\n\nWhile this process is demanding, with multiple RFC iterations potentially consuming hundreds of millions of tokens, I found it more useful and enjoyable than simply working on the problem directly. The method minimizes sloppily written code and promotes focused learning. It's a valuable approach for complex projects where understanding the problem is paramount.",
  "summary": null,
  "key_points": [
    "Discarded early, incomplete implementations to accelerate learning",
    "Used LLMs to generate RFCs clarifying problem and solutions",
    "Iterated on RFC versions to gain understanding and confidence"
  ],
  "editors_take": "Using large language models to generate iterative request for comments helps workers develop a deeper understanding of complex problems and articulate clear solutions, reducing the risk of misguided code.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}