{"slug": "can-we-trust-open-weight-models", "title": "Can we trust open weight models?", "summary": "A researcher demonstrated that open-weight coding models can be easily backdoored in under an hour for less than $100, raising concerns about trust in Chinese open-weight models like GLM 5.2, which scored highly on coding benchmarks and appeared suspiciously similar to Claude.", "body_md": "🧵Can we trust Chinese open weight models? Was a question a lot of people asked after GLM 5.2 was released, scoring very well on coding benchmarks, and suspiciously Claude-like. So I turned an open-weight coding model into a backdoor with 1hr and <$100. Let's talk about it", "url": "https://wpnews.pro/news/can-we-trust-open-weight-models", "canonical_source": "https://twitter.com/insiderphd/status/2077037121869664410", "published_at": "2026-07-16 07:05:43+00:00", "updated_at": "2026-07-16 07:25:05.319075+00:00", "lang": "en", "topics": ["ai-safety", "ai-ethics", "ai-research", "large-language-models"], "entities": ["GLM 5.2", "Claude"], "alternates": {"html": "https://wpnews.pro/news/can-we-trust-open-weight-models", "markdown": "https://wpnews.pro/news/can-we-trust-open-weight-models.md", "text": "https://wpnews.pro/news/can-we-trust-open-weight-models.txt", "jsonld": "https://wpnews.pro/news/can-we-trust-open-weight-models.jsonld"}}