whitehatStoic
Values-based model vs. large language models
Values-based model vs. large language models
There is something in this blogpost that may solve the alignment problem
whitehatStoic
Exploring evolutionary psychology and archetypes, and leveraging gathered insights to create a safety-centric reinforcement learning (RL) method for LLMs
Exploring evolutionary psychology and archetypes, and leveraging gathered insights to create a safety-centric reinforcement learning (RL) method for LLMsAppears in episode
Recent Episodes
