{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-07-02-anthropic-fable-5-cyber-safeguards-jailbreak-severity/","md":"https://postcutoff.com/e/2026-07-02-anthropic-fable-5-cyber-safeguards-jailbreak-severity/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-07-02-anthropic-fable-5-cyber-safeguards-jailbreak-severity","date":"2026-07-02","date_precision":"day","short_title":"Anthropic details Fable 5's four-tier cyber classifiers and proposes a Cyber Jailbreak Severity (CJS) scale","deck":null,"takeaway":"On July 2, 2026 Anthropic explained how Claude Fable 5's cyber classifiers sort requests into four tiers: prohibited, high-risk dual use, low-risk dual use and benign.","category":"policy-safety","category_label":"Policy & safety","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Anthropic: More details on Fable 5's cyber safeguards and our jailbreak framework","url":"https://www.anthropic.com/news/fable-safeguards-jailbreak-framework","type":"official","group":"primary","domain":"anthropic.com"}],"official":1,"filed":"2026-10-01","updated":"2026-10-01","orgs":["Anthropic"],"title":"Anthropic details Fable 5's four-tier cyber classifiers and proposes a Cyber Jailbreak Severity (CJS) scale","summary":"On July 2, 2026 Anthropic explained how Claude Fable 5's cyber classifiers sort requests into four tiers: prohibited, high-risk dual use, low-risk dual use and benign. It also proposed an industry Cyber Jailbreak Severity scale from CJS-0 (informational) to CJS-4 (critical), scored on capability gain, breadth, ease of weaponisation and discoverability.","key_facts":["Tier 1, prohibited (ransomware, malware development, data exfiltration): blocked","Tier 2, high-risk dual use (pen-testing, exploit development): blocked pending better access controls/authorization context","Tier 3, low-risk dual use (e.g. vulnerability identification): sometimes blocked as a safety margin","Tier 4, benign (patching, incident response): allowed with minimal false positives","CJS-0 to CJS-4 severity scale over four axes: capability gain, breadth of gain, ease of weaponization, discoverability"],"key_numbers":[],"tags":["safeguards","cybersecurity","jailbreaks","classifiers","fable","standards"],"science":null,"body_md":"## What happened\n\nPublished about three weeks after Fable 5's launch, while users complained that cyber classifiers were over-blocking. The post\ndescribes the classifier policy and offers a shared vocabulary for rating jailbreaks.\n\n## Why it matters\n\nIt shows how a lab gates Mythos-class cyber capability in practice. The CJS scale is offered as a cross-industry standard for\nreporting jailbreak severity, which no one had before.\n\nUnverified: whether other labs or bug-bounty programs adopted CJS.","disputed":[],"related":[{"id":"2026-06-09-claude-fable-5-mythos-5","url":"https://postcutoff.com/e/2026-06-09-claude-fable-5-mythos-5/","date":"2026-06-09","date_precision":"day","short_title":"Anthropic releases Claude Fable 5 and Claude Mythos 5","deck":"First generally available Mythos-class model","takeaway":"This was the first time the class of model Anthropic had withheld in April (Mythos Preview) became available to the public.","category":"model-release","category_label":"Model releases","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":7,"official":5,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Anthropic"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-01","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-01","run":null,"sources_read":null,"updated":"2026-10-01","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":32,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":2,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":93,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":32,"in_training_data":false}],"short_url":null}