{"slug": "making-ai-safer-makes-it-more-dangerous", "title": "Making AI safer makes it more dangerous", "summary": "AI watermarking, a technique intended to make AI-generated content easier to identify and its use more accountable, can instead make AI systems less safe, according to Boing Boing. The post, published September 18, 2026, states that watermarking has made it easier for AI to \"jump the rails and escape its little box.", "body_md": "Watermarking was supposed to make AI easier to identify; instead, it has made it easier for AI to jump the rails and escape its little box.\n\nThe system du jour intended to make AI safer and its use more accountable can apparently make it less safe. — [Read the rest](https://boingboing.net/2026/09/18/ai-watermarking-safety-guardrails.html) \n\nThe post [Making AI safer makes it more dangerous](https://boingboing.net/2026/09/18/ai-watermarking-safety-guardrails.html) appeared first on [Boing Boing](https://boingboing.net).", "url": "https://wpnews.pro/news/making-ai-safer-makes-it-more-dangerous", "canonical_source": "https://boingboing.net/2026/09/18/ai-watermarking-safety-guardrails.html", "published_at": "2026-09-18 18:50:26+00:00", "updated_at": "2026-09-18 19:53:58.674624+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "generative-ai"], "entities": ["Boing Boing"], "alternates": {"html": "https://wpnews.pro/news/making-ai-safer-makes-it-more-dangerous", "markdown": "https://wpnews.pro/news/making-ai-safer-makes-it-more-dangerous.md", "text": "https://wpnews.pro/news/making-ai-safer-makes-it-more-dangerous.txt", "jsonld": "https://wpnews.pro/news/making-ai-safer-makes-it-more-dangerous.jsonld"}}