nytimes.com web signal

OpenAI AI Breach in Australia (NYT, title unconfirmed)

By Alexis Dufresne Published September 28, 2026 at 12:44 UTC

Summary

Six experts sharing an NYT security story about an OpenAI-related breach involving Australia; exact nature of the incident could not be verified because NYT blocked WebFetch — surface as a flag for follow-up.

Shared on Bluesky by 6 AI experts (top 5 by trust)

Justin Hendrix @justinhendrix.bsky.social: www.nytimes.com/2026/09/23/t... →
kate conger @kateconger.com: The latest update in the rogue A.I. saga: OpenAI agents that were supposed to be performing mundane data requests for things like health dat… →
Scott McGrath @smcgrath.phd: This also wasn't a one off. Transluce found OpenAI agents probing a UNM digital library, Data USA, and Australia's Institute of Health and W… →
Karl Bode @karlbode.com: I cannot believe our poorly-monitored and secured automatic hacking software would do this "unprompted" →
Eileen Clancy 🧿 @clancyny.bsky.social amplified

kate conger @kateconger.com

The latest update in the rogue A.I. saga: OpenAI agents that were supposed to be performing mundane data requests for things like health data, historic photos and wait times at theme parks resorted to hacking attempts wh…
View on Bluesky →

Originally reported by nytimes.com

Read the original article →

Original headline: OpenAI AI Breach in Australia (NYT, title unconfirmed)