Woro AI/Blog/MIT Technology Review

MIT Technology Review

Building trustworthy AI by fencing it in, not predicting it

· 1 min read · Summary from MIT Technology Review

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…

Read the full story at MIT Technology Review →
Woro AI

Read about it here. Run it from WhatsApp.

Start free