{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidvyvj4umqrjr7uwwp4qjtzz4lz3nw45l4iowtuqbd7qcdijt5imm",
    "uri": "at://did:plc:mxzzpugn7bprjjrszwkbez3u/app.bsky.feed.post/3mknir6ephw22"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreihuph5gvttdjtfy35gogygeblvdlmsnzfwwpxowh5qifj4vxrilwi"
    },
    "mimeType": "image/jpeg",
    "size": 146380
  },
  "path": "/news/2026-04-everyday-devices-ai-faster-personal.html",
  "publishedAt": "2026-04-29T11:40:08.000Z",
  "site": "https://techxplore.com",
  "tags": [
    "Consumer & Gadgets"
  ],
  "textContent": "A new method developed by MIT researchers can accelerate a privacy-preserving artificial intelligence training method by about 81%. This advance could enable a wider array of resource-constrained edge devices, like sensors and smartwatches, to deploy more accurate AI models while keeping user data secure.",
  "title": "How everyday devices could train AI faster while keeping personal data on-device"
}