英伟达研究员称超大上下文窗口是死路

作者:Jonathan Kemper原标题:Nvidia researchers argue huge AI context windows are a dead end
58AI 研判分

英伟达研究团队指出,动辄百万 token 的超大上下文窗口往往既昂贵又非必要。在多项测试中,定期摘要加定向检索的效果与一次性塞入全文相当,暗示业界应重新审视“上下文越长越好”的路线。

报道正文

Nvidia researchers argue huge AI context windows are a dead end

Image description

Nano Banana Pro prompted by THE DECODER

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."

THE DECODER+