Fine-tuning, whether using RL or not, is the proverbial “cherry on the cake” and the pre-trained model captures more than 99.9% of the intelligence of the model.
I am still amazed by the strength of general models. There is the no-free lunch theorem that people use to point out that we will probably have specialized AI’s because they will be better. Current practice seems to contradict this.
This emphasis on generality makes deployment of future models a lot easier. We first build a gpt4 ecosystem. When gpt5 comes out it will be easy to implement (e.g. autogpt can run just as easy on gpt4 as on gpt5). The adaptions that are necessary are very small and thus very fast deployment of future models is to be expected.