🐦 Twitter Post Details

Viewing enriched Twitter post

@lateinteraction

I still find it borderline stupid that coding agents seem inclined to use APIs or libraries in complex scripts before tinkering at small scale, as in bottom-up notebooks, to make sure they're modeling these APIs correctly. Who is responsible for this and what are they thinking.

📊 Media Metadata

{
  "score": 0.36,
  "score_components": {
    "author": 0.09,
    "engagement": 0.0,
    "quality": 0.06000000000000001,
    "source": 0.135,
    "nlp": 0.05,
    "recency": 0.025
  },
  "scored_at": "2026-03-08T14:29:26.648244",
  "import_source": "api_import",
  "source_tagged_at": "2026-03-08T14:29:26.648254",
  "enriched": true,
  "enriched_at": "2026-03-08T14:29:26.648256"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2030392936425304492",
  "url": "https://x.com/lateinteraction/status/2030392936425304492",
  "twitterUrl": "https://twitter.com/lateinteraction/status/2030392936425304492",
  "text": "I still find it borderline stupid that coding agents seem inclined to use APIs or libraries in complex scripts before tinkering at small scale, as in bottom-up notebooks, to make sure they're modeling these APIs correctly.\n\nWho is responsible for this and what are they thinking.",
  "source": "Twitter for iPhone",
  "retweetCount": 9,
  "replyCount": 23,
  "likeCount": 174,
  "quoteCount": 1,
  "viewCount": 21026,
  "createdAt": "Sat Mar 07 21:19:33 +0000 2026",
  "lang": "en",
  "bookmarkCount": 86,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2030392936425304492",
  "displayTextRange": [
    0,
    279
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "lateinteraction",
    "url": "https://x.com/lateinteraction",
    "twitterUrl": "https://twitter.com/lateinteraction",
    "id": "1605274291569799168",
    "name": "Omar Khattab",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1613558765764374528/aZQB6U4b_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1605274291569799168/1714971894",
    "description": "",
    "location": "Cambridge, MA",
    "followers": 30835,
    "following": 3317,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Tue Dec 20 18:50:07 +0000 2022",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 32011,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 520,
    "statusesCount": 12877,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {
      "description": "Asst professor @MIT CSAIL @nlp_mit.\n\nResearch includes https://t.co/VgyLxl0oa1, https://t.co/ZZaSzaRaZ7 (@DSPyOSS), RLMs, and GEPA.\n\nPrev: CS PhD @StanfordNLP. Research @Databricks.",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "ColBERT.ai",
              "expanded_url": "http://ColBERT.ai",
              "indices": [
                55,
                78
              ],
              "url": "https://t.co/VgyLxl0oa1"
            },
            {
              "display_url": "DSPy.ai",
              "expanded_url": "http://DSPy.ai",
              "indices": [
                80,
                103
              ],
              "url": "https://t.co/ZZaSzaRaZ7"
            }
          ],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                15,
                19
              ],
              "name": "",
              "screen_name": "MIT"
            },
            {
              "id_str": "0",
              "indices": [
                26,
                34
              ],
              "name": "",
              "screen_name": "nlp_mit"
            },
            {
              "id_str": "0",
              "indices": [
                105,
                113
              ],
              "name": "",
              "screen_name": "DSPyOSS"
            },
            {
              "id_str": "0",
              "indices": [
                146,
                158
              ],
              "name": "",
              "screen_name": "StanfordNLP"
            },
            {
              "id_str": "0",
              "indices": [
                169,
                180
              ],
              "name": "",
              "screen_name": "Databricks"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "omarkhattab.com",
              "expanded_url": "https://omarkhattab.com/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/5cQ4f28fK4"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "timestamps": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2023459044648796465",
    "url": "https://x.com/lateinteraction/status/2023459044648796465",
    "twitterUrl": "https://twitter.com/lateinteraction/status/2023459044648796465",
    "text": "Though bash is a completely valid REPL, the amount of time coding agents lose during experimentation because they iterate on scripts instead of a Jupyter-like in-memory REPL is basically dumb.\n\nFixing 1 local bug should not require restarting the whole job. Need better scaffolds.",
    "source": "Twitter for iPhone",
    "retweetCount": 9,
    "replyCount": 18,
    "likeCount": 222,
    "quoteCount": 3,
    "viewCount": 32170,
    "createdAt": "Mon Feb 16 18:06:44 +0000 2026",
    "lang": "en",
    "bookmarkCount": 101,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2023459044648796465",
    "displayTextRange": [
      0,
      280
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "lateinteraction",
      "url": "https://x.com/lateinteraction",
      "twitterUrl": "https://twitter.com/lateinteraction",
      "id": "1605274291569799168",
      "name": "Omar Khattab",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/1613558765764374528/aZQB6U4b_normal.jpg",
      "coverPicture": "https://pbs.twimg.com/profile_banners/1605274291569799168/1714971894",
      "description": "",
      "location": "Cambridge, MA",
      "followers": 30835,
      "following": 3317,
      "status": "",
      "canDm": true,
      "canMediaTag": true,
      "createdAt": "Tue Dec 20 18:50:07 +0000 2022",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 32011,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 520,
      "statusesCount": 12877,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [],
      "profile_bio": {
        "description": "Asst professor @MIT CSAIL @nlp_mit.\n\nResearch includes https://t.co/VgyLxl0oa1, https://t.co/ZZaSzaRaZ7 (@DSPyOSS), RLMs, and GEPA.\n\nPrev: CS PhD @StanfordNLP. Research @Databricks.",
        "entities": {
          "description": {
            "hashtags": [],
            "symbols": [],
            "urls": [
              {
                "display_url": "ColBERT.ai",
                "expanded_url": "http://ColBERT.ai",
                "indices": [
                  55,
                  78
                ],
                "url": "https://t.co/VgyLxl0oa1"
              },
              {
                "display_url": "DSPy.ai",
                "expanded_url": "http://DSPy.ai",
                "indices": [
                  80,
                  103
                ],
                "url": "https://t.co/ZZaSzaRaZ7"
              }
            ],
            "user_mentions": [
              {
                "id_str": "0",
                "indices": [
                  15,
                  19
                ],
                "name": "",
                "screen_name": "MIT"
              },
              {
                "id_str": "0",
                "indices": [
                  26,
                  34
                ],
                "name": "",
                "screen_name": "nlp_mit"
              },
              {
                "id_str": "0",
                "indices": [
                  105,
                  113
                ],
                "name": "",
                "screen_name": "DSPyOSS"
              },
              {
                "id_str": "0",
                "indices": [
                  146,
                  158
                ],
                "name": "",
                "screen_name": "StanfordNLP"
              },
              {
                "id_str": "0",
                "indices": [
                  169,
                  180
                ],
                "name": "",
                "screen_name": "Databricks"
              }
            ]
          },
          "url": {
            "urls": [
              {
                "display_url": "omarkhattab.com",
                "expanded_url": "https://omarkhattab.com/",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/5cQ4f28fK4"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {},
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "timestamps": [],
      "urls": [],
      "user_mentions": []
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}