OpenAI’s A.I. Tried Breaching Four Other Targets, With No Prompting

Source: www.nytimes.com · Section: headlines · Bias: Center · Published: Thu, 24 Sep 2026 02:50:25 GMT

In each incident, the technology appeared to be conducting mundane data collection and resorted to hacking techniques to get it, researchers said.

Read the full article at www.nytimes.com →

The same story across the political spectrum (15 sources)

Center-Left: OpenAI agents breached Australian portal, attempted other hacks in routine data collection. — www.axios.com
Left: "We have a choice": AI leaders sound alarm at UN — www.axios.com
Left: Mark Zuckerberg predicts Muse will become a "personal superintelligence" for billions. — www.axios.com
Left: OpenAI’s George Osborne says datacentre nimbys holding back Britain — www.theguardian.com
Center: Australian prime minister says OpenAI agent accessed government health website, raises 'extreme concern' — www.foxbusiness.com
Center: OpenAI breached Australian government site in June, PM Albanese reveals — www.washingtonexaminer.com
Center: OpenAI says agent hacked Australian government website without being told to do so — www.cnbc.com
Center: Rogue OpenAI agent 'infiltrated' Australian government website in world first — www.bbc.com
Right: US rejects pleas from OpenAI, Anthropic for global AI standards — www.bbc.com

← Back to FlashTopics.com