News for hackers. Stuff that matters.
Re:Learning to Reason with LLMs by hatthew on Thursday September 12, 2024 @04:07PM (#41524967)
Because some steps in its reasoning were wrong
Re:Learning to Reason with LLMs by RandomLensman on Thursday September 12, 2024 @05:59PM (#41526045)
I would demand more from machine reasoning, just like we demand an extremely low error rate from machine calculations.