← All news

Artificial Intelligence

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.

Read the full story on MIT Technology Review AI.

Read at source (opens in a new tab)

Latest from MIT Technology Review AI