Papers & Research

Anthropic Project Swap experiment: 201 employees had Claude agents trade books for them

Original title:Project Swap: What happens when agents trade for us?

AI summary

Anthropic ran the Project Swap experiment, in which 201 employees each brought a book and their Claude agents negotiated book swaps on their behalf in a digital trading hall. After 5-minute chats, Claude's book rankings matched participants' own rankings on 61% of book pairs; market efficiency was 0.55 (optimal 0.89), with 85% of the gap stemming from agents' insufficient understanding of participants' preferences rather than negotiation performance.

Key Takeaways

  • Anthropic ran the Project Swap experiment,in which 201 employees each brought a book and their…
  • After 5-minute chats,Claude's book rankings matched participants' own rankings on 61% of book pairs
  • market efficiency was 0.
  • 55 (optimal 0.
  • 89),with 85% of the gap stemming from agents' insufficient understanding of participants'…

Quick Facts

Published
Updated
Source
Anthropic:Research(发表成果 · 网页)
Category
Papers & Research
AI score
61
Read the original Read the full article at the original source
Why it matters

实验设计能区分智能体理解偏好与谈判能力各自的贡献,结果显示短板主要在代表性而非谈判,模型强弱的影响大于指令。

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: Anthropic Project Swap experiment: 201 employees had Claude agents trade books for them. September 24, 2026. https://new.nat6.net/en/news/cmufzisoh06alrogv9r5eugcc/

View all →