One reason we trust it more than manual approval: in a study with 1,053 paid tes
Source
x.com
Author
ClaudeDevs
Date
Why it matters
Quantifies approval fatigue: human review of AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → tool calls degrades sharply over a session, which is the case for classifier-gated permissions over click-through prompts.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
