{"version":"2.1.219","anchor":"safeguard-refusal-copy-rewritten","canonical_anchor":"safeguard-refusal-copy-rewritten","heading":"Safeguard-refusal copy rewritten","tier":"notice","area":"Elsewhere","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.219\/e\/safeguard-refusal-copy-rewritten","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.219","markdown":"### Safeguard-refusal copy rewritten\n\nSafeguard refusals are now a one-liner, with longer explanations only for category-flagged cases.\n\n**What**\n\nThe message shown when a model's safeguards flag your message is shorter and no longer references a model generation, and the longer explanation is now reserved for category-flagged refusals.\n\n**Details**\n\n- the old paragraph beginning \"The safeguards are intentionally broad right now and may flag safe and routine coding, cybersecurity, or biology work\" is gone, along with the Mythos-capabilities sentence\n- the assembled string `They may flag safe, normal content as well.` was removed\n- the generic case is now a one-liner; the longer explanation appears only for category-flagged refusals\n- a cyber-category refusal, when the relevant check passes, gets its own message pointing at the Cyber Verification Program plus a dedicated support link\n- the refusal body reads \"can't respond to this message with\" rather than \"this request with\"\n\n**Evidence**\n\n`This sometimes happens with safe, normal conversations.`, `Our intentionally broad safeguards allow us to deliver more capabilities faster, but can sometimes flag legitimate coding, cybersecurity, and biology tasks.`\n\n- Area: Elsewhere\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 0\/5"}