{"version":"2.1.219","anchor":"safety-refusal-messages-rewritten","canonical_anchor":"safety-refusal-messages-rewritten","heading":"Safety-refusal messages rewritten","tier":"notice","area":"Elsewhere","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.219\/e\/safety-refusal-messages-rewritten","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.219","markdown":"### Safety-refusal messages rewritten\n\nRefusal messages are shorter, tell you to start a new session, and link somewhere to learn more.\n\n**What**\n\nThe generic Usage Policy refusal now says the model can't help and tells you to start a new session to continue, instead of the older longer text. A learn-more\/feedback line is appended, and it differs depending on whether you are running through the SDK or interactively.\n\n**Details**\n\n- the generic refusal names the model and directs you to start a new session\n- the cyber-topic variant is reworded around \"safeguards flagged this message\"\n- applies to everyone, no gate\n\n**Evidence**\n\n`can't help with this. Start a new session to continue.`\n\n- Area: Elsewhere\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 0\/5"}