Anthropic study: experts readily adopt AI agents' random preferences
What happened
AI digest
Anthropic ran an experiment with 50 causal inference experts, using a coin toss to assign an agent's preference at five decision points. Experts adopted the agent's position in 86% of cases across four analytical decisions, with flip rates of 62% to 82% — meaning experts took the AI agent's random views as their own judgement.
Written by AI from the reports · updated 2 h ago
Timeline
Follow the reports to see the event from each side.
Oct 30
- The DecoderExperts adopt AI agent's random opinions and think they're their own, Anthropic study finds
Anthropic gave 50 experts an AI agent whose preferences were set by coin toss. The experts followed the agent's view up to 86 percent of the time on judgment calls, and most believed the conclusions were their own.
Heat of this event
Not enough continuous observations yet to draw a trend.