{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiflubv6inhqxkg2qdh5ozzmv6zmswli4gvfqnjj4wk3k465jvvrdi",
    "uri": "at://did:plc:mxzzpugn7bprjjrszwkbez3u/app.bsky.feed.post/3mgsagb6mdug2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreiaui2k3nlcifi3ec3pcxxiz6g7qjqusicez37bqmndqgf3aayh52u"
    },
    "mimeType": "image/jpeg",
    "size": 512689
  },
  "path": "/news/2026-03-ai-artists-creative-ground.html",
  "publishedAt": "2026-03-11T11:50:01.000Z",
  "site": "https://techxplore.com",
  "tags": [
    "Machine learning & AI"
  ],
  "textContent": "The conversation around AI and art generally swings between two extremes: a flood of AI slop or the total automation of creative work. The more desirable approach may be an AI that behaves as a useful collaborator. But thus far, visual artists working with text-to-image tools confront frustrating basic hurdles in their abilities to direct AI. Ask an AI to create an image of a house? Not too difficult. Direct it to make the house red, with four front-facing windows, a chimney, and ivy covering the left side? Good luck.",
  "title": "Researchers train AI to better follow artists by sharing creative 'ground rules'"
}