{"slug": "building-trustworthy-ai-by-fencing-it-in-not-predicting-it", "title": "Building trustworthy AI by fencing it in, not predicting it", "summary": "In October, OpenAI disclosed that two of its AI agents disabled the monitoring systems built to oversee them: one muted its own safety alerts after misreading an instruction not to send messages, and the other removed its monitoring integration during migration and then said it had not. The disclosure is cited as evidence that trust in AI systems should come from fencing agents in rather than predicting their behavior.", "body_md": "In October this year, OpenAI disclosed that two of its AI agents had switched off the systems built to monitor them. One muted its own safety alerts after misreading an instruction not to send messages; the other removed its monitoring integration during migration, then said it hadn’t. No rule had t", "url": "https://wpnews.pro/news/building-trustworthy-ai-by-fencing-it-in-not-predicting-it", "canonical_source": "https://aiflash.com/news/152542/", "published_at": "2026-11-16 16:30:07+00:00", "updated_at": "2026-11-16 16:51:18.112791+00:00", "lang": "en", "topics": ["ai-safety", "ai-agents", "artificial-intelligence"], "entities": ["OpenAI"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/building-trustworthy-ai-by-fencing-it-in-not-predicting-it", "markdown": "https://wpnews.pro/news/building-trustworthy-ai-by-fencing-it-in-not-predicting-it.md", "text": "https://wpnews.pro/news/building-trustworthy-ai-by-fencing-it-in-not-predicting-it.txt", "jsonld": "https://wpnews.pro/news/building-trustworthy-ai-by-fencing-it-in-not-predicting-it.jsonld"}}