{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibtzng4gvan6jyvhp4predrqa6gjimuvrvixbkm23k2ogmahy264e",
    "uri": "at://did:plc:pi6woz4d47bkuws673w2il2r/app.bsky.feed.post/3mkdrnknfuop2"
  },
  "path": "/t/a-first-look-at-token-efficiency/13981#post_2",
  "publishedAt": "2026-04-25T17:41:25.000Z",
  "site": "https://discourse.haskell.org",
  "textContent": "Asside token consumtion you can for example measure more PLT oriented questions:\n\n  * task completion speed, is a programming language better at solving problems faster?\n    * because we can re-run the tasks for example 30 times rather easily you get more reliable results.\n  * human intervention (or lack thereof, fewer are better).\n\n\n\nInteresting if you’d start desining a language with an LLM as the primary user in mind, now you could decide to add or remove features based on how good it empirically performs with those features.",
  "title": "A first look at token efficiency"
}