Dev.toFrontier LLM의 Adversarial Framing 하 Tool-use 능력 상실 및 Agentic Regression 발견I Tested Claude Opus 4, GPT-4.1, GPT-4o, Sonnet 4, and Gemini 2.5 Pro on 10 Adversarial Scenarios. They All Broke on the Same One.AI/MLadvanced34 분 소요17시간 전