{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihbyemydqhj3kqcgzauasflit2zptqnlbho7dijd5r62watxlbcqi",
    "uri": "at://did:plc:ctcqaqa3tlbhfwmfefti346h/app.bsky.feed.post/3miy2ylz5tsl2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreidqapqdblminyamqfl65hyuc5vzlir5c3d72lky3fqqkdldzkn6kq"
    },
    "mimeType": "image/png",
    "size": 77931
  },
  "path": "/pro/security/a-new-frontier-model-trained-by-anthropic-that-we-believe-could-reshape-cybersecurity-project-glasswing-wants-to-use-ai-to-prevent-ai-cyberattacks-but-will-overeager-claude-mythos-do-more-damage-than-help",
  "publishedAt": "2026-04-08T09:38:20.000Z",
  "site": "https://www.techradar.com",
  "tags": [
    "Security",
    "AI Platforms & Assistants",
    "Pro"
  ],
  "textContent": "Anthropic and a number of other companies reveal Project Glasswing - which is so powerful, it won't be released publicly.",
  "title": "'A new frontier model trained by Anthropic that we believe could reshape cybersecurity': Project Glasswing wants to use AI to prevent AI cyberattacks — but will 'overeager' Claude Mythos do more damage than help?"
}