{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreig5lhwz2ni2r3kripjoeiaa4jq4hugzpggcmgw4xk5bdfmyazi4qi",
    "uri": "at://did:plc:qmoxdljeafzfhko4h2milre3/app.bsky.feed.post/3mnjxbraoh3b2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreihelgumtk4c2z4rc4ybyyrpx4reyhsilitsg67r4oi6sng34dipje"
    },
    "mimeType": "image/jpeg",
    "size": 167319
  },
  "path": "/study-ai-models-still-susceptible-to-propaganda-280990",
  "publishedAt": "2026-06-05T09:54:55.000Z",
  "site": "https://bnn-news.com",
  "tags": [
    "Social",
    "World",
    "artificial intelligence",
    "Estonia",
    "Featured",
    "propaganda",
    "Study: AI models still susceptible to propaganda",
    "Baltic News Network"
  ],
  "textContent": "A new Estonian study has found that many AI systems can still be driven by propaganda-style requests, with results varying widely depending on the model and the host, writes ERR News. As part of a broader study on the reliability of large language models (LLMs) in the Estonian context, researchers at the Estonian Language Institute […]\n\nThe post Study: AI models still susceptible to propaganda appeared first on Baltic News Network.",
  "title": "Study: AI models still susceptible to propaganda"
}