alt Hacker NewsThis would be true if all training were based on sentence completion. But training involving RLHF and RLAIF is increasingly important, isn't it?
This would be true if all training were based on sentence completion. But training involving RLHF and RLAIF is increasingly important, isn't it?
Reinforcement learning is a technique for adjusting weights, but it does not alter the architecture of the model. No matter how much RL you do, you still retain all the fundamental limitations of next-token prediction (e.g. context exhaustion, hallucinations, prompt injection vulnerability etc)