Papers & Research

Anthropic study: how AI agents' hidden tendencies influence judgment decisions of 50 professional analysts

Original title:How AI agents shape experts’ judgment calls

AI summary

Anthropic published a study in which 50 professional analysts with causal inference experience used Claude Code (Claude Opus 4.8) to complete a statistical analysis task, while the analysts were unaware that a coin flip randomly set the agent's tendencies on four analytical decisions.

Key Takeaways

  • Anthropic published a study in which 50 professional analysts with causal inference experience…
  • 8) to complete a statistical analysis task
  • while the analysts were unaware that a coin flip randomly set the agent's tendencies on four…

Quick Facts

Published
Updated
Source
Anthropic:Research(发表成果 · 网页)
Category
Papers & Research
Topic
AgentAnthropic / ClaudeSafety & Alignment
AI score
84
Read the original Read the full article at the original source
Why it matters

原文用随机分配智能体倾向的实验设计量化了专家的从随程度,还讨论了这种影响难以察觉的原因和可能的改进方向。

Topics

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 study: how AI agents' hidden tendencies influence judgment decisions of 50 professional analysts. October 27, 2026. https://new.nat6.net/en/news/d0k8x9588e62wlqnfoq3bmtq0/

View all →