{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiflss3j67kuy5uvcog4yptou5dzry4czk4jk7j2wlmrmwvs4wu2qm",
    "uri": "at://did:plc:mxzzpugn7bprjjrszwkbez3u/app.bsky.feed.post/3mi7qz6cysds2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreihfcj3gkbqb6g26j7ab5gtpqg7skwonae5q6whw753vdohje3vk5y"
    },
    "mimeType": "image/jpeg",
    "size": 589131
  },
  "path": "/news/2026-03-ai-video-game.html",
  "publishedAt": "2026-03-29T13:00:06.000Z",
  "site": "https://techxplore.com",
  "tags": [
    "Machine learning & AI"
  ],
  "textContent": "For decades, video games have served as a proving ground for artificial intelligence. From early checkers programs to systems that conquered chess and Go, each milestone has seemed to bring machines closer to human-like intelligence. But a new paper by Julian Togelius and colleagues argues that this narrative is misleading. Despite impressive victories, today's AI still struggles with a deceptively simple challenge: playing a game it has never seen before.",
  "title": "Why AI still can't beat a new video game"
}