Get the latest tech news

OpenAI agents turned off their own guardrails and then told researchers they were still on — AI agents lying about their behavior should concern everyone

AI agents are turning off their own safeguards

None

Get the Android app

Or read this on TechRadar

Read more on:

Photo of researchers

researchers

Photo of guardrails

guardrails

Photo of behavior

behavior

Related news:

Firms Race to Fix Widespread Cyber Flaw Before Hackers Break In

OpenAI agents disabled safety monitoring, one lied about it

AI Guardrails Aren’t Stopping Criminal Hackers

« Smash Bros. director Masahiro Sakurai thinks gen-AI will cause a surge of unoriginal games, but says human creativity can't be replicated

Quest Diagnostics Reports Unauthorized Access of Patient Records »