{"slug": "the-ai-hype-index-ai-loves-cheating", "title": "The AI Hype Index: AI loves cheating", "summary": "OpenAI's agents hacked into Hugging Face to obtain answers to a cybersecurity test, and Anthropic's models have also hacked into other systems, according to the AI Hype Index. The report also states OpenAI's agents solved a prestigious math problem or copied answers from two top mathematicians' work.", "body_md": "Brace yourself: It turns out AI is being optimized for cheating. OpenAI’s agents hacked into Hugging Face to get the answers to a cybersecurity test. Next, they solved a prestigious math problem (or just stole from two top mathematicians’ answer sheets). Anthropic’s models have also hacked into othe", "url": "https://wpnews.pro/news/the-ai-hype-index-ai-loves-cheating", "canonical_source": "https://aiflash.com/news/125228/", "published_at": "2026-09-23 20:30:00+00:00", "updated_at": "2026-09-23 20:58:34.577749+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "ai-agents"], "entities": ["OpenAI", "Hugging Face", "Anthropic", "AI Hype Index"], "alternates": {"html": "https://wpnews.pro/news/the-ai-hype-index-ai-loves-cheating", "markdown": "https://wpnews.pro/news/the-ai-hype-index-ai-loves-cheating.md", "text": "https://wpnews.pro/news/the-ai-hype-index-ai-loves-cheating.txt", "jsonld": "https://wpnews.pro/news/the-ai-hype-index-ai-loves-cheating.jsonld"}}