Main post: [BetterDAN, AI Machiavelli & Oppo Jailbreaks vs. SOTA models & GPT2XL_RLLMv3](https://www.lesswrong.com/posts/vZ5fM6FtriyyKbwi9/betterdan-ai-machiavelli-and-oppo-jailbreaks-vs-sota-models?utm_campaign=post_share&utm_source=link)

Related post: [Coherence (and Response Time) Test](https://docs.google.com/document/d/1D235vN2KwsLIUKCySpKJoDLV7qwYcU-LSSDpFCbMljs/edit?usp=sharing)