{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiatvyrsf357x32zvga4e47d3kom52iyhoejyrjm3q7oket67qwnme",
"uri": "at://did:plc:ksypn6kbrlwppsfny6ksos2x/app.bsky.feed.post/3mk3xf4sh4vl2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreieq3uxrh2cnjohukepzlnwlktfzta25szvn6xpgsbusiucei2xa3m"
},
"mimeType": "image/jpeg",
"size": 81959
},
"path": "/ai/anthropic-reportedly-lost-control-of-its-most-dangerous-ai-model-and-that-should-worry-everyone",
"publishedAt": "2026-04-22T16:15:15.000Z",
"site": "https://www.tomsguide.com",
"tags": [
"AI"
],
"textContent": "Anthropic is facing questions after reports claimed unauthorized users accessed Claude Mythos, its highly restricted cybersecurity AI model. Here’s why it matters.",
"title": "Anthropic reportedly 'lost control' of its most dangerous AI model — and that should worry everyone"
}