The advancement of artificial intelligence (AI) necessitates a strong emphasis on safety measures and the mitigation of risks associated with AI systems spiraling out of their creators' control. This approach aligns, to a certain extent, with prevalent practices within the contemporary technology sector. Numerous companies are harnessing the power of AI to supervise AI itself, capitalizing on the enhanced efficiency that automation brings. Studies have shown that AI may surpass human capabilities in identifying vulnerabilities within models, and this edge is expected to widen as AI technology continues to evolve and mature.