{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidpzsd7o2jh2f6f552cpl3rrqd2wmabkwhkqnyh4cvlefcpwxkoq4",
    "uri": "at://did:plc:pi6woz4d47bkuws673w2il2r/app.bsky.feed.post/3mh24xr2kfpz2"
  },
  "path": "/t/yet-another-opinion-on-llms-hasufells-blog/13775#post_17",
  "publishedAt": "2026-03-14T11:02:21.000Z",
  "site": "https://discourse.haskell.org",
  "textContent": "Interesting.\n\nI’m using those tools quite regularly in fact. Yesterday I used claude to update my nginx config to block claude bots (lol). Today I used it to set up an OpenBSD bhyve VM on my FreeBSD machine.\n\nIn both cases it would end up guessing things randomly and I constantly had to intervene and point out that:\n\n  * the config syntax is incorrect\n  * the command doesn’t exist\n  * the suggestion makes no sense\n\n\n\nTo me it seems they struggle at basic things like going through a manpage and a blog post and then assembling commands that work. Sure, you can wiggle it until it works. In those cases again… I have the opportunity to **test the output**.I’m not entirely sure if it saved me any time. I guess it’s hard to set up a proper experiment.\n\nNow, as you say… you’re using it for learning new things and this is where we probably disagree fundamentally. As soon as I ask it to explain complex or abstract things that I don’t understand myself… I have no easy means to verify **how accurate the information is**.\n\nI’ve not seen any suggestion so far on how to deal with this unknown. And given my experience, I don’t think these models only occasionally make mistakes or inaccuracies.",
  "title": "Yet another opinion on LLMs · Hasufell's blog"
}