跳到正文
The Decoder· Jonathan Kemper·· 4 小时前AI 评分52

Nvidia 研究者认为超大上下文窗口是死路

Nvidia researchers argue huge AI context windows are a dead end

AI 导读

Nvidia 研究团队认为,让模型一次性处理整本小说这类超大上下文窗口往往既过度又昂贵,在多项测试中,周期性摘要加定向查找的效果与之相当。文章指出,上下文窗口是模型的工作记忆,GPT-4 在 2023 年 3 月发布时为 8,192 tokens,如今 GPT 5.6 Sol 可处理约一百万 tokens,约为前者的 120 倍。

正文 · 原文

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."

来源:The Decoder · the-decoder.com