Sichu Lu

@lu_sichu · Twitter ·

can one of you nerds make this eval. guaranteed hit

Sichu Lu

Sichu Lu

this reminds me of an idea i had, i was using llm to roleplay D&D scenarios(do the number crunching for me, write npc stats you know the boring stuff, generate maps/images of characters. this was like a while ago. now the agents are good enough where you can make an eval that is ability to play d&d