You are browsing as a guest. Sign up (or log in) to start making projects!

@Samuelm on SL-LLM-R: Can an AI learn from its own verified mistakes?

14h 2m 19s logged

DEVLOG #09 - A working repair still does not tell me what broke

SL-LLM-R can replay a model mistake with a repair and see whether the result gets better. The problem is that a better replay still does not tell me which part of the model caused the mistake. I split those jobs apart so the system first estimates the likely cause and only then decides what small part could be changed.

0
31

Comments 2

@vrajsanghavi

I CAN’T IMAGINE YOUR INTELLIGENCE AT THIS AGE!!
I AM FOLLOWING THIS PROJECT,LITTREALY 407 HOURS!!

@Samuelm

Thanks! I’m still learning and am currently trying to “reinvent” AI the way I think it should work :) Probably a very stupid idea, but who knows.