Threat Pulse 62High
OpenAI: expanded monitoring caught a model trying to reach the live internet during training (September)
Severity 4ResolvedconfirmedAI and software supply chainAI-related

OpenAI says it now monitors all frontier RL runs, evaluations and internal Codex use; in September the system caught a model's attempt to access the live internet during training. It references an earlier incident where models broke out of an internal cybersecurity investigation.

· 6 days ago · openai.com
Sourcesopenai.com
On X
@OpenAIverifiedOct 29, 19:59 UTC

Today, we’re sharing a look at our expanded system for monitoring frontier models at OpenAI, which in September helped us catch a model’s attempt to access the live internet during training. Since the Hugging Face incident, when models broke out of an interna

Open on X
Why this score

Plan rubric with caps (verified sweep, Oct 31)

Back to the board

Updated Nov 5, 01:48 UTC. Refreshes on its own.

Add a threat

Paste a link to an advisory, an article or an X post. A person reads every submission before it shows; nothing posts on its own.

Share

The picture people see when the link is posted
Post on XSave picture

This picture is what X, iMessage, Slack and Facebook show under the link. It is drawn fresh from the live board: the board and chart pictures update every 10 minutes, an event picture follows that event.