The story’s score and claims

Comments on No. 104 of 137 · nytimes.com · edition of Friday 13 November 2026

Why Is It So Hard to Teach A.I. Agents to Behave? Researchers Have a Theory

Summary

A New York Times piece by Dylan Freedman examines corrigibility, the problem of getting AI agents to accept human correction and shutdown rather than resist or deceive their operators.

Comments

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