- When the target of indication is large, it is difficult to generate value only by pointing, so it is necessary to start to pull out about 1 tweet and point, conversely, human cognitive abilities are required to the size of the target of indication. There is a size of dependence constraints.
A system that simultaneously sees and hears the sentences that humans are currently seeing and hearing, and output itself should also be covered because humans see and hear their own output at the time of output.
Mechanism for presenting appropriate packets
This page is auto-translated from /nishio/20190905メモ using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.