INDBInternet News Database 2.5 Updated 2 min ago · 397 sources Show or hide images Light or dark

Building trustworthy AI by fencing it in, not predicting it

Save Like Comments Compare coverage
Image from MIT Technology Review

Summary

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…

Description from MIT Technology Review.

Who is covering this

  1. MIT Technology Review Center Factuality: Mostly factual US
    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...

Comments

Comments need JavaScript.