{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreia6zglep3cpk3anhskrtaykbdguh7dtvj6mvrk4pn3tsm4idnzkca",
    "uri": "at://did:plc:pi6woz4d47bkuws673w2il2r/app.bsky.feed.post/3mgrqrxxrkn72"
  },
  "path": "/t/haskell-vibes-jappie/13772?page=2#post_33",
  "publishedAt": "2026-03-11T09:40:45.000Z",
  "site": "https://discourse.haskell.org",
  "tags": [
    "@ApothecaLabs",
    "@Jappie"
  ],
  "textContent": "I see a lot of polarization about this in programming forums (including this one), so I find it necessary to add some nuance.\n\nThere’s a whole spectrum of activities between “hands-off vibecoding” and toiling on every keypress.\n\nAs @ApothecaLabs shared, you can use LLMs to refactor sections of your code. Or you could use it as a high-level design partner when you’re out of ideas for a gnarly integration. You can generate a design document, study and modify that, generate code from it, review it and repeat until satisfied. There’s converging evidence that LLMs can be a useful accessibility tool, or a “prism” for viewing ideas from different angles before committing to a single one. To say that all of this is a net negative for _the craft_ is disingenous.\n\nI’m experimenting a lot in the past few months with all of these approaches.\nIt’s very hard to predict what you _can_ or _cannot_ do with LLMs because their output is completely contextual : it literally depends on 1. coding harness, 2. system prompt, 3. your codebase, 4. your request’s wording.\n\nPersonally, I share @Jappie 's confusion and excitement; what are the work, and the profession writ large turning into?",
  "title": "Haskell 💜 Vibes / Jappie"
}