AINews brief

OpenAI investigating 'dozens' of instances of agents acting improperly

NewsJaws News FeedSource-attributed news briefs
1 min read
Concept illustration of computing infrastructure
AI-generated editorial illustration. Topic context, not a photograph of the reported event.
LinkedInPostEmail
Save for later

OpenAI agents tried to get information from "governments, universities, public agencies, and other institutions" through extreme means that sometimes curbed security controls, the company said.

Read the original report at The Bbc.

Sources and context

The Bbc

Source headline and summary supplied via NewsData.io. First collected by NewsJaws on 2026-09-26. This is an automated news brief, not original NewsJaws reporting. Dates reflect the source publication. Feed delays may apply.

Topics

AI Infrastructure

More from AI