I haven’t said that. I pointed that you can’t simply put more data into it and expect improvements. There’s definitely a lot of engineering done on the models to make them capable of using all the data.
I can give you an example. You can’t simply add more convolutional layers to a CNN and feed more images. The architectures of image models include many tricks, like inception layers.
I suspect there’re similar challenges in LLMs. And I’m not sure whether current ChatGPT can use more data to become better at reasoning, or at some point they’d need to come up with different architectures.
Mostly, you can simply stack more transformers and (as long as you have layer norm), it can train on more data (of fixed sequence length).
There are some tricks & tips, but the vast majority lie outside of the architecture improvements.
Not indefinitely, obviously. But we haven’t exhausted the available data sources yet, and the curves for prediction error vs. amount of training data strongly imply using this additional data would result in increased performance.
Do you have specific reasons for thinking that gpt-4 is near the end of this trend? I haven’t seen any compelling arguments for this.