{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreih2rdzsednelfzcy5mehouzv6nky7rkxjbs7bsojx2uxb2vet3654",
    "uri": "at://did:plc:pi6woz4d47bkuws673w2il2r/app.bsky.feed.post/3mmoh674btro2"
  },
  "path": "/t/mcp-server-for-hackage/14043#post_9",
  "publishedAt": "2026-05-25T06:22:13.000Z",
  "site": "https://discourse.haskell.org",
  "textContent": "My opinion is that the right thing is to start an ecosystem project that uses LLMs sustainably and responsibly:\n\n  * keep blocking all the scrapers and bots\n  * train our own open weight model on haskell and hackage\n  * make sure it isn’t optimized for “engagement” (optimally, an LLM for search would be able to recognize when you’re in “mindless prompting” mode and tell you to go read the docs of package XY)\n  * optimize it for search and small code snippets (“how do I do XY?”)\n  * give LICENSE warnings/summaries on non-trivial codesnippets\n\n\n\nIt’s kinda hard to use LLMs in a way that actually enables learning, but maybe someone has to try.",
  "title": "MCP server for Hackage"
}