elvis (@omarsar0) 's Twitter Profile
elvis

@omarsar0

Building with AI agents @dair_ai • Prev: Meta AI, Galactica LLM, Elastic, PaperswithCode, PhD • I also teach how to leverage and build with LLMs & AI Agents ⬇️

ID: 3448284313

linkhttps://dair-ai.thinkific.com/ calendar_today04-09-2015 12:59:26

13,13K Tweet

238,238K Takipçi

607 Takip Edilen

elvis (@omarsar0) 's Twitter Profile Photo
elvis
@omarsar0

2 years ago

Memorization vs. Generalization is one of my favorite ML research topics. One phenomenon of interest, referred to as grokking, is where models flip from memorizing to sudden generalization. A big question LLM researchers are interested in answering is whether LLMs, when trained

Memorization vs. Generalization is one of my favorite ML research topics. One phenomenon of interest, referred to as grokking, is where models flip from memorizing to sudden generalization. A big question LLM researchers are interested in answering is whether LLMs, when trained