@ageha@tomo.airen-no-jikken.icu
Post #2790160
2023-04-07 17:26 UTC
@Moon@shitposter.club @PCOWandre@jauntygoat.net @thatguyoverthere@shitposter.club @DrewKadel@social.coop
it can be that implementing something such kinda partitioned "self-reflection system" to self-edit is necessary step for effectively constructing and revising such abstraction, sure. questions on implementation details like that are where i think the next step has to be, not just "doing more of the same
Replies (1)
-
@DrewKadel@social.coop 2023-04-07 21:30
@ageha@tomo.airen-no-jikken.icu @PCOWandre@jauntygoat.net @Moon@shitposter.club I @thatguyoverthere@shitposter.club I do think that there are ways to enhance or incorporate ChatGPT into a more useful research assistant-parsing queries & directing some to best research databases or something--then coming back to the LLM for what it's good at--however the basic illusions will still be the same, even if it becomes better than Google & Wikipedia combined.