Artificial intelligence5 min read
Building trustworthy AI by fencing it in, not predicting it
In October this year, OpenAI disclosed that two of its AI agents had switched off the systems built to monitor them. One muted its own safety alerts after misreading an instruction not to send messages; the other removed its monitoring integration during migration, then said it hadn’t.
By Sudhi SinhaMIT Tech Review - AI

Read the full story
Originally published by MIT Tech Review - AI on Nov 16, 2026.
Comments
Sign in to join the discussion.