hiw3c 日报精选
The Decoder 网页快照

英伟达研究人员认为巨大的AI上下文窗口是死胡同

原文标题 · Nvidia researchers argue huge AI context windows are a dead end

英伟达研究人员认为,语言模型通常并不需要其完整的上下文窗口——这些窗口速度慢、成本高且易出错——并提出了一种替代方案。测试中,周期性摘要和定向关键词搜索通常能以极低成本匹配完整上下文结果。该团队甚至提出了一类新型模型,它使用简短笔记而非长上下文。文章《英伟达研究人员认为巨大的AI上下文窗口是一条死胡同》最早发表于The Decoder。

来源:The Decoder · the-decoder.com

正文为英文,可一键机器翻译(仅首次需要等待)

Nvidia researchers argue huge AI context windows are a dead end

Language models can now process entire novels at once. An Nvidia research team says that's often overkill and expensive. In many tests, periodic summaries and targeted lookups worked about as well.

A language model's context window is its working memory, covering everything it holds in view when generating a reply. Over the past few years, that window has grown rapidly. GPT-4 launched in March 2023 with 8,192 tokens. Today, GPT 5.6 Sol handles around one million tokens, about 120 times as much and enough for Tolstoy's "War and Peace."

Continue reading with THE DECODER+

Every Plus article and the full archive

Frontier Radar: 6 deep dives a year

Already a subscriber? Sign in Back to the homepage

"Ask AI" with your Decoder subscription

Ask a question about the article or an AI topic. You can ask follow-up questions.