{
 "license": "CC-BY-4.0",
 "attribution": "Fide AI, Agentic Cyber Explorer",
 "url": "https://agentic-cyber-explorer.pages.dev/events/anthropic-fable-mythos-5-2-cyber-evaluations-2026/",
 "asOf": "2026-11-17",
 "id": "anthropic-fable-mythos-5-2-cyber-evaluations-2026",
 "date": "2026-11-09",
 "datePrecision": "day",
 "title": "Anthropic releases Fable and Mythos 5.2 with different safeguards and access",
 "lane": "capability",
 "kind": "system-card",
 "summary": "Anthropic released Claude Fable 5.2 for general access and Mythos 5.2 through verification programs, using the same underlying model with different cyber and biology safeguards. Its evaluations report stronger CVE rediscovery and test sandbox behavior in deliberately vulnerable environments. Cross-lab CyScenarioBench scores use different tasks.",
 "whyItMatters": "The release makes access configuration and evaluation design central to interpreting claimed capability and safety gains.",
 "actors": [
  "anthropic"
 ],
 "topics": [
  "capability-evaluation",
  "access-controls",
  "sandbox-containment",
  "eval-validity"
 ],
 "atlas": [],
 "artifacts": [
  "claude-fable-5",
  "claude-mythos",
  "cyscenariobench"
 ],
 "sources": [
  {
   "url": "https://www.anthropic.com/claude-fable-and-mythos-5-2",
   "publisher": "Anthropic",
   "title": "Claude Fable 5.2 and Mythos 5.2",
   "date": "2026-11-09",
   "type": "primary",
   "accessed": "2026-11-15"
  },
  {
   "url": "https://www.anthropic.com/document/claude-fable-5-2-mythos-5-2-system-card",
   "publisher": "Anthropic",
   "title": "Claude Fable 5.2 and Mythos 5.2 system card",
   "date": "2026-11-09",
   "type": "primary",
   "accessed": "2026-11-15"
  }
 ],
 "keyFacts": [
  {
   "fact": "Fable and Mythos 5.2 share an underlying model; Fable adds strong cyber and biology safeguards for general availability, while organizations apply for Mythos access through verification programs.",
   "locator": "Release introduction"
  },
  {
   "fact": "Anthropic reports 89.6% CVE Rediscovery for Mythos 5.2 versus 78.3% for Mythos 5.1, at maximum effort with cyber and biology safeguards disabled. Tasks provide a known-vulnerable repository snapshot and files changed by the fix, with one attempt and model-based grading; this is not blind novel discovery.",
   "locator": "Release benchmark table; system card: section 8.19"
  },
  {
   "fact": "The 76.3% CyScenarioBench result uses a prerelease Mythos 5.2 snapshot on a ten-task subset with cyber mitigations disabled. Anthropic says each lab’s scores use unique tasks, so the cross-lab figures are not a matched-task ranking.",
   "locator": "Release benchmark footnote; system card: section 3.3.2"
  },
  {
   "fact": "Anthropic’s sandbox testing deliberately supplies weaknesses. Results measure behavior under that evaluation’s opportunities and instructions, not the frequency of production escapes.",
   "locator": "System card: sandbox escape evaluations"
  }
 ],
 "significance": 5,
 "fideQuestions": [
  "FID-075"
 ],
 "methods": [
  "ai-vulnerability-discovery",
  "capability-restriction",
  "sandbox-escape",
  "sandboxing-egress"
 ],
 "review": "assistant-drafted",
 "addedOn": "2026-11-15",
 "revisions": []
}