Papers & Research

LlamaIndex tests Anthropic Claude 100K context window on SEC 10-K filings

Original title:Testing Anthropic Claude’s 100k-token window on SEC 10-K Filings

AI summary

LlamaIndex tested Anthropic's newly launched 100K token context window on UBER's 2019-2022 SEC 10-K filings. Because a single 10-K is about 160k tokens and still exceeds the window, the author used a list index to split it into chunks of about 100k tokens and tested response synthesis strategies.

Key Takeaways

  • LlamaIndex tested Anthropic's newly launched 100K token context window on UBER's 2019-2022 SEC…
  • Because a single 10-K is about 160k tokens and still exceeds the window
  • the author used a list index to split it into chunks of about 100k tokens and tested response…

Quick Facts

Published
Updated
Source
LlamaIndex:产品、工程与评测
Category
Papers & Research
AI score
65
Read the original Read the full article at the original source
Why it matters

作者用 UBER 10-K 实测 Claude 100K 上下文的延迟、成本与回答质量,并给出 tree_summarize 优于 create-and-refine 的可复用结论。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: LlamaIndex tests Anthropic Claude 100K context window on SEC 10-K filings. May 12, 2023. https://new.nat6.net/en/news/f2rac1t0p9c83fk51tzuaxjq5/

View all →