🐦 Twitter Post Details

Viewing enriched Twitter post

@LiorOnAI

That's it. You can now build custom models without lifting a finger. Catalyst records every API request automatically. It sits between your app and your LLM provider. Most fine-tuned models fail in production because they train on synthetic data. This records what users actually do. No fake datasets or manual labeling needed. Training happens in four steps: 1. Use GPT-4 or Claude normally 2. Requests get captured automatically 3. Traces become labeled training data 4. Smaller models distill from usage They match frontier quality on your use case. At 95% lower inference cost and 150ms latency. Apps too expensive at frontier pricing now scale. It also creates a flywheel effect. More users means better data means better models. Every unrecorded request is training signal lost. It gives you a production-grade model trained on your actual usage, at a fraction of the cost, without building a single dataset.

View on Twitter

📊 Media Metadata

{
  "score": 0.42,
  "score_components": {
    "author": 0.09,
    "engagement": 0.0,
    "quality": 0.12,
    "source": 0.135,
    "nlp": 0.05,
    "recency": 0.025
  },
  "scored_at": "2026-04-14T22:16:20.742928",
  "import_source": "api_import",
  "source_tagged_at": "2026-04-14T22:16:20.742938",
  "enriched": true,
  "enriched_at": "2026-04-14T22:16:20.742940"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2044174981928759637",
  "url": "https://x.com/LiorOnAI/status/2044174981928759637",
  "twitterUrl": "https://twitter.com/LiorOnAI/status/2044174981928759637",
  "text": "That's it. You can now build custom models without lifting a finger.\n\nCatalyst records every API request automatically. It sits between your app and your LLM provider. \n\nMost fine-tuned models fail in production because they train on synthetic data.\n\nThis records what users actually do. \n\nNo fake datasets or manual labeling needed. \n\nTraining happens in four steps:\n\n1. Use GPT-4 or Claude normally\n2. Requests get captured automatically\n3. Traces become labeled training data\n4. Smaller models distill from usage\n\nThey match frontier quality on your use case. At 95% lower inference cost and 150ms latency.\n\nApps too expensive at frontier pricing now scale. It also creates a flywheel effect.\n\nMore users means better data means better models. Every unrecorded request is training signal lost.\n\nIt gives you a production-grade model trained on your actual usage, at a fraction of the cost, without building a single dataset.",
  "source": "Twitter for iPhone",
  "retweetCount": 0,
  "replyCount": 0,
  "likeCount": 1,
  "quoteCount": 0,
  "viewCount": 290,
  "createdAt": "Tue Apr 14 22:04:29 +0000 2026",
  "lang": "en",
  "bookmarkCount": 0,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2044174981928759637",
  "displayTextRange": [
    0,
    274
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "LiorOnAI",
    "url": "https://x.com/LiorOnAI",
    "twitterUrl": "https://twitter.com/LiorOnAI",
    "id": "931470139",
    "name": "Lior Alexander",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/2032256308196564993/ozddLZ2O_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/931470139/1761077189",
    "description": "",
    "location": "San Francisco, CA",
    "followers": 114335,
    "following": 2295,
    "status": "",
    "canDm": true,
    "canMediaTag": false,
    "createdAt": "Wed Nov 07 07:19:36 +0000 2012",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 6845,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 666,
    "statusesCount": 3808,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {
      "description": "Building the Bloomberg of AI @AlphaSignalAI (280K subs) • MIT lecturer • MILA researcher • 9 yrs in ML",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                29,
                43
              ],
              "name": "",
              "screen_name": "AlphaSignalAI"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "alphasignal.ai",
              "expanded_url": "https://alphasignal.ai",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/AyubevaLcb"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2044083606008803576",
    "url": "https://x.com/samhogan/status/2044083606008803576",
    "twitterUrl": "https://twitter.com/samhogan/status/2044083606008803576",
    "text": "Introducing Catalyst: a developer platform to monitor, train & deploy self-improving AI models\n\nbuilt for teams operating AI products at scale\n\nCatalyst can automatically:\n- collect traces from your agents\n- curate training data & evals\n- train & deploy models on par w/ Opus 4.6 https://t.co/NLHoWvhrCP",
    "source": "Twitter for iPhone",
    "retweetCount": 16,
    "replyCount": 24,
    "likeCount": 161,
    "quoteCount": 10,
    "viewCount": 17403,
    "createdAt": "Tue Apr 14 16:01:23 +0000 2026",
    "lang": "en",
    "bookmarkCount": 105,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2044083606008803576",
    "displayTextRange": [
      0,
      291
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "samhogan",
      "url": "https://x.com/samhogan",
      "twitterUrl": "https://twitter.com/samhogan",
      "id": "587016589",
      "name": "Sam Hogan 🇺🇸",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/1991286138020196357/Dhl3FgDP_normal.jpg",
      "coverPicture": "https://pbs.twimg.com/profile_banners/587016589/1759720766",
      "description": "",
      "location": "San Francisco, CA",
      "followers": 22910,
      "following": 1778,
      "status": "",
      "canDm": true,
      "canMediaTag": true,
      "createdAt": "Tue May 22 00:48:15 +0000 2012",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 13008,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 497,
      "statusesCount": 4680,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [
        "2044083606008803576"
      ],
      "profile_bio": {
        "description": "ceo @inference_net train and deploy specialized LLMs in minutes",
        "entities": {
          "description": {
            "hashtags": [],
            "symbols": [],
            "urls": [],
            "user_mentions": [
              {
                "id_str": "0",
                "indices": [
                  4,
                  18
                ],
                "name": "",
                "screen_name": "inference_net"
              }
            ]
          },
          "url": {
            "urls": [
              {
                "display_url": "inference.net",
                "expanded_url": "http://inference.net",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/gjRnSxad5X"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {
      "media": [
        {
          "allow_download_status": {
            "allow_download": true
          },
          "display_url": "pic.twitter.com/NLHoWvhrCP",
          "expanded_url": "https://twitter.com/samhogan/status/2044083606008803576/photo/1",
          "ext_media_availability": {
            "status": "Available"
          },
          "features": {
            "large": {
              "faces": []
            },
            "orig": {
              "faces": []
            }
          },
          "id_str": "2044083603110539267",
          "indices": [
            292,
            315
          ],
          "media_key": "3_2044083603110539267",
          "media_results": {
            "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARxeCzT+mrADCgACHF4LNatasPgAAA==",
            "result": {
              "__typename": "ApiMedia",
              "id": "QXBpTWVkaWE6DAABCgABHF4LNP6asAMKAAIcXgs1q1qw+AAA",
              "media_key": "3_2044083603110539267"
            }
          },
          "media_url_https": "https://pbs.twimg.com/media/HF4LNP6asAM2eD1.jpg",
          "original_info": {
            "focus_rects": [
              {
                "h": 672,
                "w": 1200,
                "x": 0,
                "y": 128
              },
              {
                "h": 800,
                "w": 800,
                "x": 200,
                "y": 0
              },
              {
                "h": 800,
                "w": 702,
                "x": 249,
                "y": 0
              },
              {
                "h": 800,
                "w": 400,
                "x": 400,
                "y": 0
              },
              {
                "h": 800,
                "w": 1200,
                "x": 0,
                "y": 0
              }
            ],
            "height": 800,
            "width": 1200
          },
          "sizes": {
            "large": {
              "h": 800,
              "w": 1200
            }
          },
          "type": "photo",
          "url": "https://t.co/NLHoWvhrCP"
        }
      ]
    },
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "timestamps": [],
      "urls": [],
      "user_mentions": []
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "communityInfo": null,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}