Agents Need an Undo Button, Not More Approval Prompts
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
The essay argues that AI agent safety should rely less on constant human approval prompts, which people rubber-stamp over time, and more on classifying each agent action by reversibility: reversible, compensable, delayable, or irreversible.