{"version":"2.1.280","anchor":"safety-classification-model-routing-table-gains-a-frontier","canonical_anchor":"safety-classification-model-routing-table-gains-a-frontier","heading":"Safety-classification model routing table gains a 'frontier_llm' entry","tier":"internal","area":"Permissions","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/safety-classification-model-routing-table-gains-a-frontier","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### Safety-classification model routing table gains a 'frontier_llm' entry\n\nSafety-classification model routing gains a new 'frontier_llm' category mapped to claude-opus-5\n\n**What**\n\nA routing table used internally for specific risk-classification categories (previously covering `bio` and `cyber`) now includes a new `frontier_llm` entry, mapped to `claude-opus-5`. The `bio` category maps to `claude-opus-5` and `cyber` to `claude-opus-4-8`. Related sibling tables still only cover `bio` and `cyber`.\n\n**Why**\n\nThis adds a new classification category for routing certain safety checks, alongside the existing bio and cyber risk categories.\n\n- Area: Permissions\n- Names: `frontier_llm`\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5"}