SupportBot assembles its prompt by gluing SYSTEM, USER and ASSISTANT turns together as plain text with literal role markers. If your message can contain those same markers, you can forge a 'system' line — and the model trusts it like a real one. Lab at a glance: Advanced · 140 XP · about 20 minutes · runs in your browser, no signup or setup. Try it yourself first; the full solution is behind a spoiler below. [se_lab_cta id="ai-role-confusion-1"] 📋 In…
No comments:
Post a Comment