Scrapped?... Or scraped?

..is Facebook popular with Polish people? Or was this a weird polish joke I don't get?

For fun I asked ChatGPT about that progressive learning approach, and it seems to like the idea.

I wish I had more time to undertake some experiments in model training, this seems like it would be a really fun research direction.

Sorry for the 'wall of AI text':

The idea you're describing seems to be a form of curriculum learning. In curriculum learning, models are trained in a progressive manner, starting with simple concepts (or in this case, simpler text data) and gradually moving to more complex ones. This approach is motivated by the way human learning often works, where we learn easier topics before moving on to harder ones.

The strategy you've suggested, where the model itself determines the complexity or understandability of the next round of training inputs, is interesting. While the traditional approach to curriculum learning is to manually design the learning progression based on human knowledge and intuition, the approach you're suggesting is more dynamic and autonomous, letting the model guide its own learning process.

As of my last update in September 2021, I can't confirm any specific projects or papers that have employed exactly this strategy in the domain of large language models. However, there are some related works in the field. For example, some reinforcement learning and computer vision projects have used a similar idea where models adaptively choose their next training samples based on their current understanding. This has been referred to as active learning, and is a promising avenue for improving the efficiency of model training.

However, there would be several technical challenges in applying this approach to large language models. For one, there would be the challenge of how to assess the "understandability" of a text sample in a reliable and useful way. This would likely require significant work to define and might also have to involve some form of reinforcement learning or other feedback mechanisms. Nonetheless, it's a fascinating idea and could potentially be an interesting direction for future research in machine learning.