{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreia63ajjfrqzejbz3q5iioc4hpkvhu2tdn3menwko5gzdd25w27ujy",
    "uri": "at://did:plc:pi6woz4d47bkuws673w2il2r/app.bsky.feed.post/3mh2fxckzevo2"
  },
  "path": "/t/yet-another-opinion-on-llms-hasufells-blog/13775#post_21",
  "publishedAt": "2026-03-14T20:51:58.000Z",
  "site": "https://discourse.haskell.org",
  "textContent": "Ambrose:\n\n> hallucinates\n\nDitto on hallucinations - it is so easy to lead it into spewing garbage; I can tell that it is garbage because I have a lot of experience in eg that particular domain, but ye gods, the ease with which it generates something that to a layman sounds valid and even ‘has results’ in a cursory search, and all its really done is blend two fields because its confused one homonym in one field for another - it gives me pause.\n\nIt isn’t so much that it can’t generate useful and _correct_ output (it can, especially for tasks that have been completed before), its that it first and foremost generates _plausible_ output, so I heavily lean in favor of the difficulty of verifying the correctness of the output as being an inhibition to the use of AI, distinct from the moral issues of how they trained it.\n\nSo, best used like a smart autocomplete for rote syntactic transformations, organization and search, and nomenclature suggestions, rather than deep pontificating. I swear it spends half the energy generating empty platitudes about how amazing my approach is and how deep my questions are, because at their core those corporate AIs are not designed to answer your questions, they are designed to keep you using them, and making you feel like they answered your question is how they go about doing that regardless of what the output actually was.\n\nBut for those limited tasks, where they can not escape into some imaginary hallucinated domain, they are very helpful.",
  "title": "Yet another opinion on LLMs · Hasufell's blog"
}