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
- Category
- Papers & Research
- AI score
- 61
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.
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/