{
  "type": "tweet",
  "id": "2039834316013031909",
  "url": "https://x.com/jerryjliu0/status/2039834316013031909",
  "twitterUrl": "https://twitter.com/jerryjliu0/status/2039834316013031909",
  "text": "This is exactly what I've been doing with Claude Code.\n\nThe biggest bottleneck with my ability to use these agents is ensuring they preserve relevant context between relevant sessions. Having the agent output files in .md and .html is not only a nicer way to view outputs than in the terminal, but also a good way to preserve context for future sessions.\n\nalso been using Obsidian to view locally generated .md files\n\nthe only slight hiccup is that the native harnesses aren't amazing at handling non-plaintext files (.pdf, .pptx, and more); the open-source skills use libraries that aren't optimized for generating readable text from complex layout docs. \n\nwe built liteparse for this purpose to replace pypdf/pymupdf (https://t.co/JNER0mVcB8) i use it as part of my local claude code harness",
  "source": "Twitter for iPhone",
  "retweetCount": 7,
  "replyCount": 7,
  "likeCount": 158,
  "quoteCount": 2,
  "viewCount": 20715,
  "createdAt": "Thu Apr 02 22:36:13 +0000 2026",
  "lang": "en",
  "bookmarkCount": 179,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2039834316013031909",
  "displayTextRange": [
    0,
    279
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "jerryjliu0",
    "url": "https://x.com/jerryjliu0",
    "twitterUrl": "https://twitter.com/jerryjliu0",
    "id": "369777416",
    "name": "Jerry Liu",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1283610285031460864/1Q4zYhtb_normal.jpg",
    "coverPicture": "",
    "description": "",
    "location": "",
    "followers": 72024,
    "following": 1467,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Wed Sep 07 22:54:31 +0000 2011",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 8590,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1466,
    "statusesCount": 6801,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2038733178689782222"
    ],
    "profile_bio": {
      "description": "document OCR + workflows @llama_index. cofounder/CEO\n\nCareers: https://t.co/EUnMNmb4DZ\nEnterprise: https://t.co/Ht5jwxRU13",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "llamaindex.ai/careers",
              "expanded_url": "https://www.llamaindex.ai/careers",
              "indices": [
                63,
                86
              ],
              "url": "https://t.co/EUnMNmb4DZ"
            },
            {
              "display_url": "llamaindex.ai/contact",
              "expanded_url": "https://www.llamaindex.ai/contact",
              "indices": [
                99,
                122
              ],
              "url": "https://t.co/Ht5jwxRU13"
            }
          ],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                25,
                37
              ],
              "name": "",
              "screen_name": "llama_index"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "llamaindex.ai",
              "expanded_url": "https://www.llamaindex.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/YiIfjVl1ly"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": {
    "binding_values": [
      {
        "key": "photo_image_full_size_large",
        "value": {
          "image_value": {
            "height": 419,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=800x419",
            "width": 800
          }
        }
      },
      {
        "key": "thumbnail_image",
        "value": {
          "image_value": {
            "height": 200,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=400x400",
            "width": 400
          }
        }
      },
      {
        "key": "description",
        "value": {
          "string_value": "A fast, helpful, and open-source document parser. Contribute to run-llama/liteparse development by creating an account on GitHub."
        }
      },
      {
        "key": "domain",
        "value": {
          "string_value": "github.com"
        }
      },
      {
        "key": "thumbnail_image_large",
        "value": {
          "image_value": {
            "height": 300,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=600x600",
            "width": 600
          }
        }
      },
      {
        "key": "summary_photo_image_small",
        "value": {
          "image_value": {
            "height": 202,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=386x202",
            "width": 386
          }
        }
      },
      {
        "key": "thumbnail_image_original",
        "value": {
          "image_value": {
            "height": 600,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=orig",
            "width": 1200
          }
        }
      },
      {
        "key": "site",
        "value": {
          "scribe_key": "publisher_id",
          "user_value": {
            "id_str": "13334762",
            "path": []
          }
        }
      },
      {
        "key": "photo_image_full_size_small",
        "value": {
          "image_value": {
            "height": 202,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=386x202",
            "width": 386
          }
        }
      },
      {
        "key": "summary_photo_image_large",
        "value": {
          "image_value": {
            "height": 419,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=800x419",
            "width": 800
          }
        }
      },
      {
        "key": "thumbnail_image_small",
        "value": {
          "image_value": {
            "height": 72,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=144x144",
            "width": 144
          }
        }
      },
      {
        "key": "thumbnail_image_x_large",
        "value": {
          "image_value": {
            "height": 600,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=png&name=2048x2048_2_exp",
            "width": 1200
          }
        }
      },
      {
        "key": "photo_image_full_size_original",
        "value": {
          "image_value": {
            "height": 600,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=orig",
            "width": 1200
          }
        }
      },
      {
        "key": "photo_image_full_size_alt_text",
        "value": {
          "string_value": "A fast, helpful, and open-source document parser. Contribute to run-llama/liteparse development by creating an account on GitHub."
        }
      },
      {
        "key": "vanity_url",
        "value": {
          "scribe_key": "vanity_url",
          "string_value": "github.com"
        }
      },
      {
        "key": "photo_image_full_size",
        "value": {
          "image_value": {
            "height": 314,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=600x314",
            "width": 600
          }
        }
      },
      {
        "key": "summary_photo_image_alt_text",
        "value": {
          "string_value": "A fast, helpful, and open-source document parser. Contribute to run-llama/liteparse development by creating an account on GitHub."
        }
      },
      {
        "key": "thumbnail_image_color",
        "value": {
          "image_color_value": {
            "palette": [
              {
                "percentage": 88.38,
                "rgb": {
                  "blue": 255,
                  "green": 255,
                  "red": 255
                }
              },
              {
                "percentage": 4.32,
                "rgb": {
                  "blue": 198,
                  "green": 120,
                  "red": 49
                }
              },
              {
                "percentage": 3.98,
                "rgb": {
                  "blue": 0,
                  "green": 0,
                  "red": 0
                }
              },
              {
                "percentage": 0.51,
                "rgb": {
                  "blue": 251,
                  "green": 122,
                  "red": 129
                }
              },
              {
                "percentage": 0.37,
                "rgb": {
                  "blue": 243,
                  "green": 136,
                  "red": 217
                }
              }
            ]
          }
        }
      },
      {
        "key": "title",
        "value": {
          "string_value": "GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser"
        }
      },
      {
        "key": "summary_photo_image_color",
        "value": {
          "image_color_value": {
            "palette": [
              {
                "percentage": 88.38,
                "rgb": {
                  "blue": 255,
                  "green": 255,
                  "red": 255
                }
              },
              {
                "percentage": 4.32,
                "rgb": {
                  "blue": 198,
                  "green": 120,
                  "red": 49
                }
              },
              {
                "percentage": 3.98,
                "rgb": {
                  "blue": 0,
                  "green": 0,
                  "red": 0
                }
              },
              {
                "percentage": 0.51,
                "rgb": {
                  "blue": 251,
                  "green": 122,
                  "red": 129
                }
              },
              {
                "percentage": 0.37,
                "rgb": {
                  "blue": 243,
                  "green": 136,
                  "red": 217
                }
              }
            ]
          }
        }
      },
      {
        "key": "summary_photo_image_x_large",
        "value": {
          "image_value": {
            "height": 600,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=png&name=2048x2048_2_exp",
            "width": 1200
          }
        }
      },
      {
        "key": "summary_photo_image",
        "value": {
          "image_value": {
            "height": 314,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=600x314",
            "width": 600
          }
        }
      },
      {
        "key": "photo_image_full_size_color",
        "value": {
          "image_color_value": {
            "palette": [
              {
                "percentage": 88.38,
                "rgb": {
                  "blue": 255,
                  "green": 255,
                  "red": 255
                }
              },
              {
                "percentage": 4.32,
                "rgb": {
                  "blue": 198,
                  "green": 120,
                  "red": 49
                }
              },
              {
                "percentage": 3.98,
                "rgb": {
                  "blue": 0,
                  "green": 0,
                  "red": 0
                }
              },
              {
                "percentage": 0.51,
                "rgb": {
                  "blue": 251,
                  "green": 122,
                  "red": 129
                }
              },
              {
                "percentage": 0.37,
                "rgb": {
                  "blue": 243,
                  "green": 136,
                  "red": 217
                }
              }
            ]
          }
        }
      },
      {
        "key": "photo_image_full_size_x_large",
        "value": {
          "image_value": {
            "height": 600,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=png&name=2048x2048_2_exp",
            "width": 1200
          }
        }
      },
      {
        "key": "card_url",
        "value": {
          "scribe_key": "card_url",
          "string_value": "https://t.co/JNER0mVcB8"
        }
      },
      {
        "key": "summary_photo_image_original",
        "value": {
          "image_value": {
            "height": 600,
            "url": "https://pbs.twimg.com/card_img/2039735812896817152/l2Fu11Rt?format=jpg&name=orig",
            "width": 1200
          }
        }
      }
    ],
    "card_platform": {
      "platform": {
        "audience": {
          "name": "production"
        },
        "device": {
          "name": "iPhone",
          "version": "13"
        }
      }
    },
    "name": "summary_large_image",
    "url": "https://t.co/JNER0mVcB8",
    "user_refs_results": [
      {
        "rest_id": "13334762",
        "result": {
          "__typename": "User",
          "action_counts": {
            "favorites_count": 8668
          },
          "avatar": {
            "image_url": "https://pbs.twimg.com/profile_images/1633247750010830848/8zfRrYjA_normal.png"
          },
          "banner": {
            "image_url": "https://pbs.twimg.com/profile_banners/13334762/1765308302"
          },
          "core": {
            "created_at": "Mon Feb 11 04:41:50 +0000 2008",
            "name": "GitHub",
            "screen_name": "github"
          },
          "dm_permissions": {
            "can_dm": true
          },
          "exclusive_tweet_following": false,
          "follow_request_sent": false,
          "identity_profile_labels_highlighted_label": {},
          "location": {
            "location": "San Francisco, CA"
          },
          "media_permissions": {
            "can_media_tag": true
          },
          "notifications_settings": {
            "notifications_enabled": false
          },
          "pinned_items": {
            "tweet_ids_str": [
              "2019093909981257849"
            ]
          },
          "privacy": {
            "protected": false,
            "suspended": false
          },
          "private_super_following": false,
          "profile_bio": {
            "description": "The AI-powered developer platform to build, scale, and deliver secure software.",
            "entities": {
              "description": {
                "hashtags": [],
                "symbols": [],
                "urls": [],
                "user_mentions": []
              },
              "url": {
                "urls": [
                  {
                    "display_url": "github.com",
                    "expanded_url": "http://github.com",
                    "indices": [
                      0,
                      23
                    ],
                    "url": "https://t.co/bbJgfyzKzp"
                  }
                ]
              }
            }
          },
          "profile_image_shape": "Square",
          "profile_metadata": {
            "profile_interstitial_type": "",
            "profile_link_color": "981CEB"
          },
          "profile_translation": {
            "translator_type_enum": "None"
          },
          "properties": {
            "has_extended_profile": true
          },
          "relationship_counts": {
            "followers": 2627471,
            "following": 334
          },
          "relationship_perspectives": {
            "blocked_by": false,
            "blocking": false,
            "followed_by": false,
            "following": false,
            "live_following": false,
            "muting": false
          },
          "rest_id": "13334762",
          "smart_blocked_by": false,
          "smart_blocking": false,
          "super_follow_eligible": false,
          "super_followed_by": false,
          "super_following": false,
          "tweet_counts": {
            "media_tweets": 2940,
            "tweets": 10465
          },
          "verification": {
            "is_blue_verified": true,
            "verified": false,
            "verified_type": "Business"
          },
          "website": {
            "url": "https://t.co/bbJgfyzKzp"
          }
        }
      }
    ]
  },
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "github.com/run-llama/lite…",
        "expanded_url": "https://github.com/run-llama/liteparse",
        "indices": [
          720,
          743
        ],
        "url": "https://t.co/JNER0mVcB8"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2039805659525644595",
    "url": "https://x.com/karpathy/status/2039805659525644595",
    "twitterUrl": "https://twitter.com/karpathy/status/2039805659525644595",
    "text": "LLM Knowledge Bases\n\nSomething I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:\n\nData ingest:\nI index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally \"compile\" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.\n\nIDE:\nI use Obsidian as the IDE \"frontend\" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).\n\nQ&A:\nWhere things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.\n\nOutput:\nInstead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up \"filing\" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always \"add up\" in the knowledge base.\n\nLinting:\nI've run some LLM \"health checks\" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.\n\nExtra tools:\nI find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. \n\nFurther explorations:\nAs the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM \"know\" the data in its weights instead of just context windows.\n\nTLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.",
    "source": "Twitter for iPhone",
    "retweetCount": 1072,
    "replyCount": 687,
    "likeCount": 10616,
    "quoteCount": 263,
    "viewCount": 890595,
    "createdAt": "Thu Apr 02 20:42:21 +0000 2026",
    "lang": "en",
    "bookmarkCount": 15599,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2039805659525644595",
    "displayTextRange": [
      0,
      275
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "karpathy",
      "url": "https://x.com/karpathy",
      "twitterUrl": "https://twitter.com/karpathy",
      "id": "33836629",
      "name": "Andrej Karpathy",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/1296667294148382721/9Pr6XrPB_normal.jpg",
      "coverPicture": "https://pbs.twimg.com/profile_banners/33836629/1407117611",
      "description": "",
      "location": "Stanford",
      "followers": 2061169,
      "following": 1080,
      "status": "",
      "canDm": true,
      "canMediaTag": true,
      "createdAt": "Tue Apr 21 06:49:15 +0000 2009",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 23041,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 863,
      "statusesCount": 10082,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [
        "1617979122625712128"
      ],
      "profile_bio": {
        "description": "I like to train large deep neural nets. Previously Director of AI @ Tesla, founding team @ OpenAI, PhD @ Stanford.",
        "entities": {
          "description": {
            "hashtags": [],
            "symbols": [],
            "urls": [],
            "user_mentions": []
          },
          "url": {
            "urls": [
              {
                "display_url": "karpathy.ai",
                "expanded_url": "https://karpathy.ai",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/0EcFthjJXM"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {},
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "urls": [],
      "user_mentions": []
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}