跳到正文
The Decoder· Jonathan Kemper·· 3 小时前AI 评分40

Nvidia 研究者称超大 AI 上下文窗口是死路一条

Nvidia researchers argue huge AI context windows are a dead end

AI 导读

Nvidia 研究团队认为,超大上下文窗口往往是过度且昂贵的方案,定期摘要加定向检索在多项测试中效果相当。GPT-4 于 2023 年 3 月发布时上下文为 8,192 tokens,而如今 GPT 5.6 Sol 可处理约 100 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