MIT Technology Review

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…

By MIT Technology Review

1 min read
Building trustworthy AI by fencing it in, not predicting it
AI-generated illustration

Got news to share with the events industry?

Submit a press release or story tip and reach thousands of event professionals.

Get in touch→

More in AI, Machine Learning & GenAI

Related Insights