René's URL Explorer Experiment

{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"AI usage memo","articleBody":"recipes, from time-consuming experience\n\nerrors:\n- prompting too simple: the AI doesn't respect any rule and can change things you don't want at first (like variable names)\n- not using multi-AI loost the comparison and compensation (like orthographic errors, what is generated different is what to look)\n- an easy  before/after comparison test is usefull, better when they can auto-check themself, simpler if they write auto-test\n- not adding safe exit to llm , \"do you think it's possible ? is there enough information to\", may reduce hallucinations\n- accepting torents of lines of  code... as AI can bloat you also on this\n\ntotal time saver:\n- asking AI to not disrupt existing code: \"can you help rework it so it can do current feature and new one ?\" \n\nnext level things:\n- [GitHub Copilot for Skeptics Who Still Think AI is Overrated](https://youtu.be/anI4Hr-ag80): explains some AI beginner errors\n\n\nThis parodic picture summarizes well the standard pitfalls when using IA too blindly\n\n![Image](https://github.com/user-attachments/assets/bd0799cc-04ed-4101-b28a-7dd364543191)\n","author":{"url":"https://github.com/stonebig","@type":"Person","name":"stonebig"},"datePublished":"2025-05-30T13:10:24.000Z","interactionStatistic":{"@type":"InteractionCounter","interactionType":"https://schema.org/CommentAction","userInteractionCount":5},"url":"https://github.com/1624/winpython/issues/1624"}