https://www.lesswrong.com/posts/TcfyGD2aKdZ7Rt3hk/alignment-pretraining-ai-discourse-causes-self-fulfilling
LLMs pretrained on data about misaligned AIs themselves become less aligned. Luckily, pretraining LLMs with synthetic data about good AIs helps them become more aligned.
thank you
https://www.lesswrong.com/posts/TcfyGD2aKdZ7Rt3hk/alignment-pretraining-ai-discourse-causes-self-fulfilling
thank you