{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiabmafygt5dixgcnc4lxdyzhv2oytwkj5kizxoy6acmz7y4n4fbqa",
    "uri": "at://did:plc:i243uudlyj6njfil6ddywa7k/app.bsky.feed.post/3mk7r5447zf42"
  },
  "path": "/2026/04/23/anthropics-too-dangerous-ai-was-accessed-by-guessing-the-url.html",
  "publishedAt": "2026-04-23T23:05:49.000Z",
  "site": "https://boingboing.net",
  "tags": [
    "Post",
    "AI",
    "anthropic",
    "cybersecurity",
    "hype",
    "Technology",
    "according to The Register",
    "Read the rest",
    "Anthropic's \"too dangerous\" AI was accessed by guessing the URL",
    "Boing Boing"
  ],
  "textContent": "That Linux kernel bug Anthropic highlighted as proof of Mythos's hacking prowess? Researcher Devansh found it was actually discovered by Claude Opus 4.6 — Anthropic's publicly available model — not by the restricted Mythos. The find is buried in a 244-page system card that independent researchers have been dissecting since the April 7 announcement, and it's one of several places where the hype doesn't hold up, according to The Register. — Read the rest \n\nThe post Anthropic's \"too dangerous\" AI was accessed by guessing the URL appeared first on Boing Boing.",
  "title": "Anthropic's \"too dangerous\" AI was accessed by guessing the URL"
}