ChipokiaTech news, without the noise
← All stories

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…

Preview courtesy of MIT Technology Review. The full article opens on their site.

More from MIT Technology Review