I like the idea of trying out H-JEPA with GFlowNet actors.
I also like the idea of using LLM-based virtue ethics as a regularizer, although I would still want deontic guardrails that seem good enough to avoid catastrophe.
I like the idea of trying out H-JEPA with GFlowNet actors.
I also like the idea of using LLM-based virtue ethics as a regularizer, although I would still want deontic guardrails that seem good enough to avoid catastrophe.