🐦 Twitter Post Details

Viewing enriched Twitter post

@jkronand

Stanfords DSPy is the best high level LLM programing framework I have seen this far. Langchain never resonated with me; despite being an early LLM framework, its design and abstractions felt overly complex. DSPy, on the other hand, is a huge step in the right direction. DSPy provides a simple approach to defining retrieval and reasoning sequences, using high-level abstractions. It also includes many built in features like "compiling" for prompt adjustments and model fine-tuning, all in a straightforward Pythonic syntax. https://t.co/3ZEW7DG6S3

🔧 Raw API Response

{
  "user": {
    "created_at": "2008-03-11T12:27:29.000Z",
    "default_profile_image": false,
    "description": "Narrow AI optimist.✨Former Head of ML at Nines, Former Head of synthetic data at Scale AI 💫",
    "fast_followers_count": 0,
    "favourites_count": 11349,
    "followers_count": 2786,
    "friends_count": 989,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 81,
    "location": "Palo Alto, CA",
    "media_count": 109,
    "name": "Joel Kronander",
    "normal_followers_count": 2786,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/14122266/1687762512",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1635756469986689024/lPOWrGg5_normal.jpg",
    "screen_name": "jkronand",
    "statuses_count": 2515,
    "translator_type": "none",
    "verified": false,
    "withheld_in_countries": [],
    "id_str": "14122266"
  },
  "id": "1705844313765364193",
  "conversation_id": "1705844313765364193",
  "full_text": "Stanfords DSPy is the best high level LLM programing framework I have seen this far. \n\nLangchain never resonated with me; despite being an early LLM framework, its design and abstractions felt overly complex. DSPy, on the other hand, is a huge step in the right direction.\n\nDSPy provides a simple approach to defining retrieval and reasoning sequences, using high-level abstractions. It also includes many built in features like \"compiling\" for prompt adjustments and model fine-tuning, all in a straightforward Pythonic syntax.\n\nhttps://t.co/3ZEW7DG6S3",
  "reply_count": 11,
  "retweet_count": 98,
  "favorite_count": 718,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/F6xdlVBawAA9hbV.png",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/jkronand/status/1705844313765364193",
  "created_at": "2023-09-24T07:19:12.000Z",
  "#sort_index": "1705844313765364193",
  "view_count": 125359,
  "quote_count": 7,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://twitter.com/jkronand/status/1705844313765364193"
}