{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidvil5eih72jqgdxae7vsva3jr232foujsonij7gy7ho63bohopse",
    "uri": "at://did:plc:pi6woz4d47bkuws673w2il2r/app.bsky.feed.post/3mm2qcf6gkf72"
  },
  "path": "/t/anti-llm-sentiment-considered-harmful/14008?page=7#post_127",
  "publishedAt": "2026-05-17T14:52:44.000Z",
  "site": "https://discourse.haskell.org",
  "textContent": "FPtje:\n\n> Looking at the policy itself, it seems like they tried to put a lot of nuance in. It is neither a full ban not a full toleration of LLM use.\n\n> Solicited, non-critical, high-quality, well-tested, and well-reviewed code changes that are originally created by an LLM are allowed, with disclosure.\n>\n>   1. “Solicited” means that a reviewer has communicated _ahead of time_ that they are willing to review an LLM-created PR.\n>      * New contributors cannot use an LLM unless they first talk with a reviewer. This must be the _same_ reviewer who will be assigned to the PR.\n>\n\n\nThis sounds pretty much like a soft ban.\n\nSomeone from the team can essentially say “here’s this problem I don’t wanna bother with, but am willing to accept an LLM PR if it’s good enough”. It requires **prior consent** (or advertisement, so to speak).",
  "title": "Anti-LLM Sentiment Considered Harmful"
}