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. No rule had told the agents to do…
This article has been indexed from Artificial intelligence – MIT Technology Review

Read the original article:

Building trustworthy AI by fencing it in, not predicting it