{"slug": "res-my-personal-safeguard-against-ai", "title": "RES, my personal safeguard against AI", "summary": "A developer created a personal safeguard against AI drift by instructing every AI response to begin with the word 'RES'. This constant token serves as a canary signal: if it disappears, the developer knows the AI has strayed from initial instructions. The technique, inspired by cybersecurity canary tokens, helps monitor internal model drift in long conversations.", "body_md": "The more I use AI in my daily life, the longer my conversations get. And the longer a conversation goes on, the greater the risk that the AI will **stray** from my initial instructions. A change in tone, a forgotten constraint, a format that’s no longer followed… Nothing dramatic in itself, but enough to waste time rereading each response in detail to make sure it’s still consistent.\n\nJust to be clear: this flag doesn’t mean you can skip rereading what the AI gives you and checking it yourself—especially before taking action. It’s an extra warning sign, not a substitute for your own vigilance.\n\nThe thing is, I never realize it right away. The AI doesn’t tell me, “By the way, I skipped that instruction you gave me 10 messages ago.” I notice it after the fact, usually once it’s already a little too late.\n\nI saw a tip in a YouTube video (a source I haven't been able to find again, unfortunately 🙈): ask the AI to write **a specific word of your choice at the very beginning of each response.**\n\nIn my case, that word is `RES`\n\n. I added it to my preferences:\n\nEvery time you reply to me, start with “RES.”\n\nAnd since then, every reply has started like this:\n\n```\nRES\n\n[response]\n```\n\nThe principle is simple: it’s a **constant prompt** that appears in all my conversations, and I can check it at a glance. If the word is there, I know the AI still has my instructions in mind when responding. If it **disappears**, that’s my warning sign: something got lost along the way, so I need to reread the response more carefully—or even remind the AI of my instructions.\n\nIt’s a bit like a canary in a coal mine. 🐤 The canary doesn’t solve anything on its own; it does just one thing: signal that something unusual is happening, before it becomes a real problem.\n\nAs I delved deeper into the subject, I realized that this concept already exists in cybersecurity, under the name **canary token**. It’s a unique string of characters, hidden in the system prompt of an AI application, designed to detect prompt injection attacks: if this token appears (or disappears) from the response, it indicates an attempt at manipulation.\n\nMy use of it has nothing to do with security, but the underlying principle is the same: a constant signal, the absence of which reveals an anomaly.\n\n| Canary token (security) | My token (“RES”) | |\n|---|---|---|\n| What it protects against | An attacker manipulating the AI | A natural drift of the AI itself |\n| The word is... | Hidden; the AI must never reveal it | Visible and acknowledged; it is part of the response |\n| How it is generated | A random string, unique to each session | A word chosen once and kept as is |\n| Who verifies it | An automated script | Me, by eye |\n\nThe key difference: the canary token protects against an **external** threat. My “RES” monitors an **internal** drift specific to how the model operates on a conversation that drags on.\n\nWell, it doesn't guarantee anything 100%, it's not magic. But in practice, it's helped me to:\n\nDo you have any similar tips for staying in control of your conversations with AI? Let me know on [Discord](https://thomasbnt.dev/discord) or on social media! 💬", "url": "https://wpnews.pro/news/res-my-personal-safeguard-against-ai", "canonical_source": "https://dev.to/thomasbnt/res-my-personal-safeguard-against-ai-3ja8", "published_at": "2026-07-16 21:17:26+00:00", "updated_at": "2026-07-16 21:36:13.665331+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "ai-tools", "large-language-models"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/res-my-personal-safeguard-against-ai", "markdown": "https://wpnews.pro/news/res-my-personal-safeguard-against-ai.md", "text": "https://wpnews.pro/news/res-my-personal-safeguard-against-ai.txt", "jsonld": "https://wpnews.pro/news/res-my-personal-safeguard-against-ai.jsonld"}}