Andrei Amatuni
@awndrei.bsky.social
PhD student in the Preston Lab @ UT Austin. Studying learning, memory and neural computation
This framework for thinking about emergent skills in LLMs seems promising arxiv.org/abs/2307.15936
A Theory for Emergence of Complex Skills in Language Models
A major driver of AI products today is the fact that new skills emerge in language models when their parameter set and training corpora are scaled up. This phenomenon is poorly understood, and a mecha...
arxiv.org
January 25, 2025 at 1:51 PM
This framework for thinking about emergent skills in LLMs seems promising arxiv.org/abs/2307.15936