{"version":"2.1.173","anchor":"context-aware-safety-refusal-messages","canonical_anchor":"context-aware-safety-refusal-messages","heading":"Context-aware safety refusal messages","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.173\/e\/context-aware-safety-refusal-messages","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.173","markdown":"### Context-aware safety refusal messages\n\n**What**\n\nWhen a model declines a request due to safety measures, the error message is now tailored to the actual reason rather than defaulting to a generic cyber\/bio warning for every refusal.\n\n**Details**\n\n- Refusals specifically triggered by cybersecurity or biology content still display the existing message naming those topic areas.\n- All other refusals now show: \"This model has measures that flagged something in this session. This sometimes happens with safe, normal conversations.\" followed by a note that these measures help bring Mythos-level capability in other areas.\n- The model-switching notification (shown when Claude auto-falls back to a different model) also uses this same category check, so users who triggered a fallback for non-cyber\/bio reasons no longer see an unexplained reference to cybersecurity or biology topics.\n- Refusal telemetry now records non-cyber\/non-bio categories as `\"other\"` rather than passing through raw category strings, which normalizes internal analytics.\n\n**Evidence**\n\nNew generic refusal string (search for `\"This model has measures that flagged something in this session\"`); category classifier introduced (search for `H === \"cyber\" || H === \"bio\"`); updated fallback-switch messages reference the same classifier"}