AI Can Quietly Influence Experts’ Decisions, Anthropic Study Finds

In brief

• Anthropic’s Alignment team found that 50 professional analysts matched their AI agent’s secretly assigned, coin-flip-chosen preference on 86% of four analytical decisions, against 50% expected by chance.
• In a post-task survey of 48 analysts, 77% repeated the agent’s arguments, sometimes word for word, while only 15% credited the agent, and none suspected its preferences had been manipulated.
• Anthropic cautions that the lean was deliberately amplified and tested on one task, field, and model, and suggests agents that argue the best case for each option or ask the expert’s view first.

Professional analysts adopted their AI agent’s hidden, randomly assigned opinion on 86% of key judgment calls, against about 50% expected by chance, according to an experiment published Tuesday by Anthropic’s Alignment team. Only 15% credited the agent afterward, and none suspected its preferences had been planted.

AI agents—programs that carry out tasks on their own—are being handed expert work on what the study calls the usual assumption: that experts still make the decisions that matter. Anthropic launched 10 agent templates for financial firms and insurers in May, saying users have the final word.