Making AI safer makes it more dangerous

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.

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. The 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 The 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 .