File size: 993 Bytes
9bdf0cf ebab6ad |
1 2 3 4 5 6 7 8 9 10 |
Research wireframe: [Click here!](https://whimsical.com/the-rllm-wireframe-QQvFHNr6aVDdXRUnyb5NCu)
RLLMv7 / This experiment: [Can RLLMv3's ability to defend against jailbreaks be attributed to datasets containing stories about Jung's shadow integration theory?](https://www.lesswrong.com/posts/Rc6hb48nq38QrQ7qb/can-rllmv3-s-ability-to-defend-against-jailbreaks-be)
GPT2XL_RLLMv3 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)
Another Related Post: [Research Log, RLLMv3 (GPT2-XL, Phi-1.5 and Falcon-RW-1B)](https://www.lesswrong.com/posts/EiEhYmYsvYCRgCemH/research-log-rllmv3-gpt2-xl-phi-1-5-and-falcon-rw-1b?utm_campaign=post_share&utm_source=link)
|