{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicuhfapl5ka7xxhckp7p7knov6jbmnhep4zx4upoq3lnu2ett6nri",
    "uri": "at://did:plc:pi6woz4d47bkuws673w2il2r/app.bsky.feed.post/3ml6ri5barlu2"
  },
  "path": "/t/anti-llm-sentiment-considered-harmful/14008?page=4#post_67",
  "publishedAt": "2026-05-06T11:14:58.000Z",
  "site": "https://discourse.haskell.org",
  "textContent": "dschrempf:\n\n> If you write code as a hobby, of course, nobody will force you to use an agent.\n\nNo one can force me to use an agent, whether it’s at home or at work.\n\nThis is also what I tell my clients.\n\ndschrempf:\n\n> But if you write code for a living, you have to compete with others that use agents.\n\nNo, I really don’t.\n\nI think we need to take a step back and resist the FOMO, the aggressive marketing of tech CEOs and so on.\n\nI’m not really sure how everything is going to evolve, but this narrative is deeply toxic.\n\nI think we’re going to be left behind if we:\n\n  * don’t fix the haskell tooling\n  * continue to write insufficient documentation\n  * don’t improve the onboarding story\n  * can’t maintain a stable ecosystem\n\n\n\nand most importantly, which is overarching all of this: **let’s make Haskell fun to write**. This language was developed by humans, for humans.\n\nCoincidentally, I think all these points would also make Haskell more suitable for LLMs. So how about we worry about those instead?",
  "title": "Anti-LLM Sentiment Considered Harmful"
}