{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihumzymhthhnjv5uqbids53pqi3ztlnxxg45i3nruyhh5z67gzjdy",
    "uri": "at://did:plc:pi6woz4d47bkuws673w2il2r/app.bsky.feed.post/3mgrk37p5dn32"
  },
  "path": "/t/haskell-vibes-jappie/13772?page=2#post_31",
  "publishedAt": "2026-03-11T08:30:47.000Z",
  "site": "https://discourse.haskell.org",
  "textContent": "ocramz:\n\n> You can run an LLM on your desktop workstation, in particular one trained with fully open and/or synthetic data.\n\nNot one that comes even close to being useful for anything more than auto-completing individual lines or at most small boilerplate snippets, in my experience. I haven’t even restricted myself to ethically trained models, just free local ones.",
  "title": "Haskell 💜 Vibes / Jappie"
}