Afer Robot, Do You Really Need to Have Interacted With a Door Knob Before?

Canjune: It takes a lot of effort just to do reinforcement learning, already incorporating a very expensive language model whose knowledge is still not that easy to extract. So it does seem like there are a lot of unantwered questions there. Are there any things that people listening might be able to help you with, like future collaborators, datus as tools, open questions, open problems? Yes, i think i've said, i don't know many times throughout the session already. And so if any one does know, in answer to any of those things that i said, i'd love to get anemalen as well as corrections to anything that i said wrong.