Our readingWhat is a korrent?
Mixture-of-experts models can scale stably but begin to show fundamental limits as they are scaled further.
Drawn from what Gwern said
What these subjects mean
scaling laws Whether more compute keeps buying more capability, and where the curve now bends -- pre-training, post-training, test-time.
neural networks The architecture almost all modern machine learning is built on, and what changes when it gets deeper.