{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidrj7xpu66nabsyaus3c7njdxguksslxkjnnsu3yofspr73zhgtpa",
    "uri": "at://did:plc:pi6woz4d47bkuws673w2il2r/app.bsky.feed.post/3mh4j5huloby2"
  },
  "path": "/t/yet-another-opinion-on-llms-hasufells-blog/13775?page=2#post_29",
  "publishedAt": "2026-03-15T14:36:52.000Z",
  "site": "https://discourse.haskell.org",
  "textContent": "My sense is that part of the disparity between opinion comes from the ideological positions on the nature of intelligence that the two camps have here. That is, if you believe that LLMs are a fancy autocomplete that merely imitates semantic content, I think you’ll tend to interpret its failures as evidence of a lack of reasoning ability (rather than a more anthropomorphic explanation like: it didn’t have enough context to know what to do).\n\nI tend to agree with the scepticism about their ability to do genuinely difficult tasks without a lot of context. But I’m not really convinced that it stems from a fundamental problem with the technology; do we really have a clear enough characterization of what reasoning is to be able to say that LLMs are not doing it? Rather, I would say that they often reason rather well, and also often fail to reason.",
  "title": "Yet another opinion on LLMs · Hasufell's blog"
}