@lintool
I profess CS-ly at @UWaterloo. Previously, I monkeyed code for @Twitter, slides for @Cloudera, and scienced for @yupp_ai.
AI
The authors call the reranker competitive and say most experiments used no more than a handful of GPUs.
AI
One post jokes that “grep is all you need” and “BM25 is all you need” have both been “+1ed by LLMs”—then adds, “wait, I meant peers.”
AI
The paper’s arXiv description highlights how leaderboards such as LMArena turn human preferences between pairs of language models into rankings.
