{"slug": "how-easily-can-russian-propaganda-fool-ai-models-a-new-benchmark-finds-out", "title": "How easily can Russian propaganda fool AI models? A new benchmark finds out", "summary": "The Institute of the Estonian Language released a benchmark to measure how susceptible AI language models are to Russian propaganda, revealing significant vulnerabilities in current systems.", "body_md": "The Institute of the Estonian Language has released a benchmark measuring how susceptible AI language models are to Russian propaganda.\n\nThe article [How easily can Russian propaganda fool AI models? A new benchmark finds out](https://the-decoder.com/how-easily-can-russian-propaganda-fool-ai-models-a-new-benchmark-finds-out/) appeared first on [The Decoder](https://the-decoder.com).", "url": "https://wpnews.pro/news/how-easily-can-russian-propaganda-fool-ai-models-a-new-benchmark-finds-out", "canonical_source": "https://the-decoder.com/how-easily-can-russian-propaganda-fool-ai-models-a-new-benchmark-finds-out/", "published_at": "2026-06-16 11:28:13+00:00", "updated_at": "2026-06-16 11:51:30.573861+00:00", "lang": "en", "topics": ["ai-safety", "large-language-models", "ai-policy", "natural-language-processing"], "entities": ["Institute of the Estonian Language"], "alternates": {"html": "https://wpnews.pro/news/how-easily-can-russian-propaganda-fool-ai-models-a-new-benchmark-finds-out", "markdown": "https://wpnews.pro/news/how-easily-can-russian-propaganda-fool-ai-models-a-new-benchmark-finds-out.md", "text": "https://wpnews.pro/news/how-easily-can-russian-propaganda-fool-ai-models-a-new-benchmark-finds-out.txt", "jsonld": "https://wpnews.pro/news/how-easily-can-russian-propaganda-fool-ai-models-a-new-benchmark-finds-out.jsonld"}}