{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicdm3jg4hwa3dgxxp56p3lhm7mlx7snmoa6ujezadg5rzhivi3pb4",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mjrxskmeqjc2"
  },
  "path": "/t/human-centred-agentic-intelligence-hai-a-three-layer-framework-for-designing-human-agent-system-journeys/175362#post_4",
  "publishedAt": "2026-04-18T17:13:08.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "A Million Random Digits with 100,000 Normal Deviates | RAND",
    "https://github.com/Ernst03"
  ],
  "textContent": "Yeah I was into attempting to compress random binary back in the days.\nThat data set is based on the RAND A Million Random Digits with 100,000 Normal Deviates | RAND\n\nI presented my best effort in 2014 : https://github.com/Ernst03\nSo kind of a crazy thing to dedicate to as a workingman but nonetheless useful today in this conversation.\n\nMark Nelson, of data compression lore, was the lead voice in debunking shysters claiming to compress random data. This was before the proper Internet; on Usenet. He made the put-up-or-shutup challenge and I found it the “Cat’s Meow” for my interests.\nIt has been the dataset of my life for all my information science quests. I was a layman; a man of manual labor career.\n\nHowever for you, if you have not been advised of limit cycles this is informative.\nThis “Dynamic Unary Encoding” simply counts runs of same parity in a finite binary and reports the counts in terminated unary encoding.\n\nI am aware that now that LLM-Ai is here, that I can draw upon that wealth and present a better paper in the future.\nHowever, I can answer questions presented.\nIt simply is a datatype.\n\n-Ernst",
  "title": "Human-Centred Agentic Intelligence (HAI): A Three-Layer Framework for Designing Human-Agent-System Journeys"
}