{"channel":"tech","content":"I find myself dreaming about \"replace Wikipedia\" again.\r\n\r\n----\r\n\r\nWhat does it take to replace Wikipedia?\r\n\r\n# A base of 50k \"decent\" encyclopedia articles. ChatGPT or a dozen other LLMs can do this.\r\n# A way to generate articles on current events. How will the *machine* know things? You collect primary sources, and write the article based on them. ( a \"primary\" source is a source with direct connections to an event. Despite the protests of many Wikipedia editors, contemporary news articles are generally primary sources. A \"secondary\" source analyzes the primary sources, with the benefit of hindsight. A \"tertiary\" source is an encyclopedia or the like, built on secondary sources.) ( the need to prefer secondary sources on Wikipedia is for multiple reasons; one of them is that editors can easily mis-interpret primary sources. hopefully the machine can avoid this problem) ( the problems of \"who creates the primary sources we use\" are more difficult)\r\n# A way to encourage people to use your site and not others. ( \"advertising spend\" can do this. Also, appealing to a vertical (or clique) that dislikes Wikipedia can generate word-of-mouth marketing) ( the cynical approach would be to have a dozen different encyclopedias, targeting a dozen different cliques)\r\n# A way to generate revenue. ( Wikipedia, famously, has no ads [other than the annual donation-drive banners])\r\n# A way to remain up to date.\r\n\r\n----\r\n\r\nThe new encyclopedia would use hypertext. Maybe. ( my experience has demonstrated that most people are less enamored by hypertext than I am)\r\n","created_at":"2025-01-15T21:55:53.233009","id":108,"llm_annotations":{},"parent_id":null,"processed_content":"

I find myself dreaming about \"replace Wikipedia\" again.\r

What does it take to replace Wikipedia?\r

\n
    \n
  • A base of 50k \"decent\" encyclopedia articles. ChatGPT or a dozen other LLMs can do this.\r
    • \n
  • A way to generate articles on current events. How will the machine know things? You collect primary sources, and write the article based on them. \u2699\ufe0f( a \"primary\" source is a source with direct connections to an event. Despite the protests of many Wikipedia editors, contemporary news articles are generally primary sources. A \"secondary\" source analyzes the primary sources, with the benefit of hindsight. A \"tertiary\" source is an encyclopedia or the like, built on secondary sources.) \ud83d\udca1( the need to prefer secondary sources on Wikipedia is for multiple reasons; one of them is that editors can easily mis-interpret primary sources. hopefully the machine can avoid this problem) \ud83d\udca1( the problems of \"who creates the primary sources we use\" are more difficult)\r
    • \n
  • A way to encourage people to use your site and not others. \ud83d\udca1( \"advertising spend\" can do this. Also, appealing to a vertical (or clique) that dislikes Wikipedia can generate word-of-mouth marketing) \ud83d\udd25( the cynical approach would be to have a dozen different encyclopedias, targeting a dozen different cliques)\r
    • \n
  • A way to generate revenue. \u2699\ufe0f( Wikipedia, famously, has no ads [other than the annual donation-drive banners])\r
    • \n
  • A way to remain up to date.\r
    • \n

The new encyclopedia would use hypertext. Maybe. \ud83d\udd25( my experience has demonstrated that most people are less enamored by hypertext than I am)\r

","quotes":[],"subject":"blue danube"}