The story’s score and claims

Comments on No. 79 of 122 · Quaspar · edition of Tuesday 17 November 2026

Agents Need an Undo Button, Not More Approval Prompts

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.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules