News for hackers. Stuff that matters.
Re:LLMs cannot find reasoning errors, but can correct them by kromem on Tuesday November 21, 2023 @11:58PM (#38374904)
Well, let me know when "true AI" arrives.

Until then, I'll make sure to be mindful of conventions.

(And just a reminder, but organic intelligence has its own conventions that work when aligned with and cause issues when misaligned with, so your expectations of universal general purpose without advantages to one approach or another may be unrealistic.)

There are no comments on this comment yet.