Nov 23, 2023
Illustrating Reinforcement Learning from Human Feedback (RLHF)
Posted by Cecile G. Tamura in category: robotics/AI
Q* appears to apply a RL technique that uses AI generated data and teaches LLMs how to solve multi step logic problems Q* techniques can be applied to GPT-5 endowing it with excellent reasoning and retrieval skills This may not be AGI but it is an extremely powerful LLM.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.