Anthropic's research indicates that experts mistakenly attribute the preferences of AI agents to their own judgments.
Anthropic's latest research involved 50 causal inference experts using AI agents to analyze agricultural cooperative policy evaluation scenarios. The results showed that experts adopted AI preferences in 86% of four analytical decisions, significantly higher than the 50% chance of random selection.
A controlled experiment with 50 causal inference experts quantified the implicit impact of AI recommendations on expert judgment and the extent to which it was unnoticed.
Same story1 other outlet also reported this
- The Decoder··First
Anthropic research finds that experts will adopt the random views of AI agents and consider them their own judgments
- ITHome · AI··+11 h 0 min·Reading now
Anthropic's research indicates that experts mistakenly attribute the preferences of AI agents to their own judgments.
Adds:median time reduced by 25 minutes
In order of publication · later reports are added as they appear · Compared by AI from each outlet’s title and summary
Source: ITHome · AI · ithome.com