Gary Ang (Ming) (@simplyboringai): "I need to eat my words. I just explained that LLMs are static after training and can’t truly adapt to new information after training. Google’s new paper “Nested Learning: The Illusion of Deep Learning Architectures” shows a path beyond that limitation."

I need to eat my words.

I just explained that LLMs are static after training and can’t truly adapt to new information after training.

Google’s new paper “Nested Learning: The Illusion of Deep Learning Architectures” shows a path beyond that limitation.

Nested Learning: The Illusion of Deep Learning Architectures

Nov 24

9:53 PM