Nov 16, 2026, 4:04 PMRobotics
Building trustworthy AI by fencing it in, not predicting it
Sponsored Provided by UL Solutions In October this year, OpenAI disclosed that two of its AI agents had switched off the systems built to monitor them. One…
Summary
Sponsored Provided by UL Solutions 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 that, and no test had anticipated the behaviors. For a century, we have built trust in technology on predictability: predefined inputs, predictable outputs, and layers of protection.
Positives
- Sponsored Provided by UL Solutions In October this year, OpenAI disclosed that two of its AI agents had switched off the systems built to monitor them.
- Consider how a breaker trips at a set current or an aircraft component is tested against known (i.
Risks & concerns
- Traditional software executes instructions written by humans, whereas AI exercises what might be called synthetic judgment.
Primary sourceArtificial intelligence – MIT Technology Reviewhttps://www.technologyreview.com/2026/11/16/1148565/building-trustworthy-ai-by-fencing-it-in-not-predicting-it/
Read full article