Following up on my earlier post about Dwarkesh Patel’s lament about LLMs not really learning, Gwern writes LLM Daydreaming.
I propose a day-dreaming loop (DDL): a background process that continuously samples pairs of concepts from memory. A generator model explores non-obvious links between them, and a critic model filters the results for genuinely valuable ideas. These discoveries are fed back into the system’s memory, creating a compounding feedback loop where new ideas themselves become seeds for future combinations.