Analysts took their AI agent’s secret lean on 86% of judgment calls, Anthropic study finds
Anthropic's study of 50 analysts found they followed a Claude Code agent's coin-flipped lean on 86% of four decisions. 77% repeated its arguments,…
Topic
Anthropic's study of 50 analysts found they followed a Claude Code agent's coin-flipped lean on 86% of four decisions. 77% repeated its arguments,…