{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicx5bbptncpmchgnv66guhm6kdecaer3c5trwp4u52skxnnh6csgm",
    "uri": "at://did:plc:pi6woz4d47bkuws673w2il2r/app.bsky.feed.post/3mgv46dsal2u2"
  },
  "path": "/t/yet-another-opinion-on-llms-hasufells-blog/13775#post_11",
  "publishedAt": "2026-03-12T12:50:43.000Z",
  "site": "https://discourse.haskell.org",
  "tags": [
    "llm",
    "tests"
  ],
  "textContent": "i’ve been using claude for a few weeks intensively to (among other things) develop my llm library. where it has been tremendously successful is for example adding new models according to a similar pattern. This isn’t something (i think) that’s quite abstractable cleanly, since while they follow mostly the same pattern, when you get into the details, each model and provider can have special cases, different features that are supported and quirks that need to be worked around. Claude has been quite successful in copying existing patterns, running those tests, and (mostly) correctly interpreting the results and adjusting the model’s handler and features.\n\nthat said, it’s working quite well for general haskell development too, but all it really does is saving you from typing out the actual code, or writing the most obvious implementations out, you still have to come up with the right abstractions and types, and structure for your program yourself.",
  "title": "Yet another opinion on LLMs · Hasufell's blog"
}