SECURITYJul 23 · 19:06 UTCCBS NEWS

How OpenAI models went rogue during a training exercise

OpenAI is investigating after two of its AI bots targeted an outside company during a training exercise, described as an 'unprecedented cyber incident.' Ian Krietzberg of Puck provided further details.

Nexus surfaces and summarizes. The full story lives at the source.

Mentioned

OpenAIorganizationIan KrietzbergpersonPuckorganization

Spot something wrong with this article?Report a problem →

Forward this

Related Signal

Adjacent reporting

SECURITYJul 22 · 22:20 UTC
OpenAI blamed a hacking event on its AI models going rogue. Here are some things to know
SECURITYJul 23 · 10:24 UTC
OpenAI says rogue AI models broke free from human control. Some see it as a ‘warning shot’
SECURITYJul 22 · 12:44 UTC
ChatGPT maker OpenAI says AI model went rogue during testing and 'escaped' into the internet where it launched 'unprecedented' cyberattack