{
  "id": 9883186,
  "title": "How to keep enjoying programming in a world of LLMs",
  "url": "https://urgent.news/2026/09/25/how-to-keep-enjoying-programming-in-a-world-of-llms",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-25T23:22:27.000Z",
  "source": {
    "name": "Lobsters",
    "slug": "lobsters",
    "url": "https://discourse.haskell.org/t/how-to-keep-enjoying-programming-in-a-world-of-llms/14705"
  },
  "original_language": "en",
  "account": "The article \"How to keep enjoying programming in a world of LLMs\" provides strategies to maintain enjoyment and productivity in programming while incorporating large language models (LLMs). The author expresses concerns about potential AI burnout and fear of losing jobs to less skilled programmers aided by LLMs. They note that the code quality in projects may be compromised due to LLM-assisted development, but argue that humans still play a crucial role in the software creation process.\n\nThe author suggests that rather than completely relying on LLMs for coding, programmers should use them for non-coding tasks such as generating to-do lists, organizing test results, and tracking planning items. They recommend maintaining a human-like involvement in the coding process to prevent skill loss and ensure code quality. The author emphasizes that LLMs are not good at producing human-readable code and can easily make mistakes. Therefore, it is essential for programmers to understand the domain they are working in better than the LLMs.\n\nThe article also cautions against letting LLMs make crucial decisions or fully handle research tasks. Instead, the author encourages programmers to do their own research in parallel, ensuring they have enough context before engaging with LLMs. This approach aims to improve productivity while preserving the enjoyment and skill level of the programmer.",
  "summary": null,
  "key_points": [],
  "editors_take": null,
  "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."
}