Eric Winsor

Oct 31, 2024 | lesswrong.com | Lucas Teixeira |Lauren Greenspan |Dmitry Vaintrob |Eric Winsor

AI safety is a young science. In its early history, deep and speculative questions regarding the risks of artificial superintelligence attracted the attention of basic science and philosophy, but the near-horizon focus of industry and governance, coupled with shorter safety timelines, means that applied science is now taking a bigger hand in the field’s future.

Dec 13, 2023 | arxiv.org | Eric Winsor

[Submitted on 13 Dec 2023] Title:Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models Download a PDF of the paper titled Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models, by Alexandre Variengien and Eric Winsor Download PDF HTML (experimental) Abstract:When solving challenging problems, language models (LMs) are able to identify relevant information from long and complicated contexts.